SlideShare una empresa de Scribd logo
1 de 24
2022.03.18
Neural Approximate Dynamic Programming for
On-Demand Ride-Pooling
Sanket Shah, Meghna Lowalekar, Pradeep Varakantham
AAAI ’19
Hongkyu Lim
Contents
• Introduction
• Background
• Ride-pool Matching
Problem(RMP)
• NeurADP: Neural Approximate
Dynamic Programming
• Experiment
• Results
3
Introduction
• On-Demand Ride- Pooling Unlike Taxi-on-Demand (ToD)
• Benefits
a) Reducing costs
b) Making more money per trip
c) Covering more # of passengers with the same or less # of cars
• Ride-Pool Matching Problem(RMP)
• Markov Decision Process
• Approximate Dynamic Programming(ADP)
• Integer Linear Program(ILP)
• Deep Reinforcement Learning (Use of Neural Network in approximating
value function by connecting it to Reinforcement Learning)
4
Introduction
1) Relying on the traditional planning approaches to model the RMP
• It does not scale to on-demand city-scale scenarios.
2) Greedy search mechanism
• It does not consider the impact of a given assignment on future assignments.
3) Reinforcement Learning to address myopic assignments
• It cannot be extended to deal with the task when vehicles get more than one
passenger at a time.
4) Approximate Dynamic Programming framework to solve the ToD problem
• Linear Program does not hold for the RMP with arbitrary vehicle capacities.
• Current ADP does not consider cases in which vehicles are already partially filled
with prior passengers.
The constraints the researchers ran into in the past 😫
5
Introduction
1) Arbitrary capacity RMP problem as an ADP
2) Proposign Neural ADP(NeurADP)
• A general ADP method that can learn value functions.
(approximated using Neural Networks) from ILP based assignment
problems.
3) Bring techniques from Deep Q-Networks to improve the stability and
scalability of NeurADP
Contributions 🥴
6
Background
1) A framework based on Markov Decision Process(MDP) model
 ADP tackles large multi-period stochastic fleet optimization
problems.
Approximate Dynamic Programming(ADP)
• MDP :
• ADP :
7
Ride-pool Matching Problem (RMP)
1) Passenger Fleet matching algorithm
 Consider a fleet of vehicles with Random initial locations.
How to serve requests with the provided number of vehicles?
• 𝒢 ∶ Road Network. (ℒ, ℰ) (set of street intersections ,adjacency of
intersections)
• 𝒰 ∶ Combination of requests
• ℛ ∶ Vehicles or resources
• 𝒟 ∶ Set of constraints on delay  {𝜏, 𝜆}
• Δ ∶ Decision epoch duration
• 𝒪 : Objective  Number of Car-pooling cases
8
NeurADP
<Schematic outlining overall NeurADP>
Neural Approximate Dynamic Programming (NeurADP)
9
NeurADP
<Steps>
A. Get requests based on NYC Taxi dataset
B. Map the requests and their combinations to vehicles
1) Vehicles serve them under the constraints defined by 𝒟 to create
feasible actions
C. Score each of these feasible actions using Neural Network Value
Function
Neural Approximate Dynamic Programming (NeurADP)
10
NeurADP
<Steps>
D. Create a mapping of requests to vehicles that maximises the sum of
scores generated in (C) using the Integer Linear Program(ILP)
E. Use this final mapping to update the score function
F. Simulate the motion of vehicles until the next epoch
Neural Approximate Dynamic Programming (NeurADP)
11
NeurADP
• 1 to 1 mapping for ToD is a simple task operated in Linear
Programming.
• However, many to 1 mapping is hard.
• 2 cases
• Single empty vehicle
• Partially filled vehicle
• The task needs to be solved with respect to unexpected
occurrences.
• It cannot be solved with Linear Programming.
Approximate Dynamic Programming(ADP)
12
NeurADP
• Past work in ADP for ToD uses the dual values to update the
parameters of their value function approximation.
• The best action in optimizing RMP is to apply Integer Linear
Program(ILP)
• ILP has bad LP-relaxations
• We cannot use LP-dual to update our value function.
• Consequently, we connect ADP to Reinforcement Learning.
• Use the more general Bellman update to optimize the value
function.
No more LP-duals
13
NeurADP
• Past work in ADP addresses high dimensionality by hand-crafted
attributes(ex. Aggregated number of vehicles in each location.)
• It’s okay… for ToD because it is one-to-one mapping.
• However, how about RMP?
• Each vehicle has different number of passengers going to
multiple different locations…
• Use Neural Network based value function to automatically learn a
compact low dimensional representation of the large state space.
Curse of Dimensionality 😵💫
14
NeurADP
• Naïve approaches to approximating Neural Network value functions in
Deep Reinforcement Learning is unstable.
• Replace LP-duals with more general Bellman update for stepping up
the Neural Network value function
• It’s named “Neural ADP”.
🥴 Challenges of learning a Neural Network value function
15
NeurADP
• 2 Steps for constraints
1. Constraints at the vehicle level
 Satisfying delay constraints 𝒟 and vehicle capacity constraints
2. Constraints at the system level
 Each request is assigned to at most one vehicle.
How to handle exponential action space?
16
Experiments
• Setting up the constraints
• The maximum allowed waiting time 𝜏 : 120 - 420 seconds
• The number of vehicles ℛ : 1000 - 3000
• Capacity : 2 – 10 passengers
• The value of maximum allowable detour delay 𝜆 : 2 * 𝜏
• The decision epoch duration Δ : 60 seconds
• Baselines
• ZAC algorithm
• TBF-Complete by Lowalekar et. al.
• TBF-Heuristic by the author’s group
Comparing the performance of NeurADP to leading approaches for solving RMP
17
Experiments
• Dataset
• New York Yellow Taxi Dataset 2016
• Road network : osmnx with ‘drive’ network type
• In total, 4373 nodes & 9540 edges
• Manhattan only
• Pickup time is converted to approximate decision epoch based on
Δ.
• On average, 322,714 requests in a day
• 19820 requests during peak hour
Comparing the performance of NeurADP to leading approaches for solving RMP
18
Results
• Dataset
• New York Yellow Taxi Dataset 2016
• Road network : osmnx with ‘drive’ network type
• In total, 4373 nodes & 9540 edges
• Manhattan only
• Pickup time is converted to approximate decision epoch based on
Δ.
• On average, 322,714 requests in a day
• 19820 requests during peak hour
The goal is to serve more requests trying not to be too greedy. 🥴
19
Results
The goal is to serve more requests trying not to be too greedy. 🥴🥴 ❗️😵
20
Results
The constraints might affect the result? 🥴
21
Results
The constraints might affect the result?
Effect of changing the tolerance to delay, 𝜏
• The lower 𝜏 makes it difficult to accept new requests
•  It’s more important to consider future requests when 𝜏 is lower.
22
Results
The constraints might affect the result?
Effect of changing the capacity
• The higher capacity a vehicle has, the larger scope for improvement of the system
along with the future requests is taken into account.
23
Results
The constraints might affect the result?
Effect of changing the number of vehicles
• The quality of assignments plays a smaller role because there will always be a
vehicle to serve the request.
Thank you

Más contenido relacionado

Similar a Neural Approximate Dynamic Programming for On-Demand Ride-Pooling

PRM-RL: Long-range Robotics Navigation Tasks by Combining Reinforcement Learn...
PRM-RL: Long-range Robotics Navigation Tasks by Combining Reinforcement Learn...PRM-RL: Long-range Robotics Navigation Tasks by Combining Reinforcement Learn...
PRM-RL: Long-range Robotics Navigation Tasks by Combining Reinforcement Learn...Dongmin Lee
 
Driving Behavior for ADAS and Autonomous Driving IV
Driving Behavior for ADAS and Autonomous Driving IVDriving Behavior for ADAS and Autonomous Driving IV
Driving Behavior for ADAS and Autonomous Driving IVYu Huang
 
Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...
Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...
Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...ivaderivader
 
APRICOT 2017: Trafficshifting: Avoiding Disasters & Improving Performance at ...
APRICOT 2017: Trafficshifting: Avoiding Disasters & Improving Performance at ...APRICOT 2017: Trafficshifting: Avoiding Disasters & Improving Performance at ...
APRICOT 2017: Trafficshifting: Avoiding Disasters & Improving Performance at ...Michael Kehoe
 
Trafficshifting: Avoiding Disasters & Improving Performance at Scale
Trafficshifting: Avoiding Disasters & Improving Performance at ScaleTrafficshifting: Avoiding Disasters & Improving Performance at Scale
Trafficshifting: Avoiding Disasters & Improving Performance at ScaleAPNIC
 
Driving Behavior for ADAS and Autonomous Driving V
Driving Behavior for ADAS and Autonomous Driving VDriving Behavior for ADAS and Autonomous Driving V
Driving Behavior for ADAS and Autonomous Driving VYu Huang
 
A Dynamic Logistic Dispatching System With Set-Based Particle Swarm Optimization
A Dynamic Logistic Dispatching System With Set-Based Particle Swarm OptimizationA Dynamic Logistic Dispatching System With Set-Based Particle Swarm Optimization
A Dynamic Logistic Dispatching System With Set-Based Particle Swarm OptimizationRajib Roy
 
MSCV Capstone Spring 2020 Presentation - RL for AD
MSCV Capstone Spring 2020 Presentation - RL for ADMSCV Capstone Spring 2020 Presentation - RL for AD
MSCV Capstone Spring 2020 Presentation - RL for ADMayank Gupta
 
Towards Auto-Extracting Car Park Structures: Image Processing Approach on Low...
Towards Auto-Extracting Car Park Structures: Image Processing Approach on Low...Towards Auto-Extracting Car Park Structures: Image Processing Approach on Low...
Towards Auto-Extracting Car Park Structures: Image Processing Approach on Low...Poo Kuan Hoong
 
Highly Accurate Alignment of Data from Measurement Trains:

 the Challenges o...
Highly Accurate Alignment of Data from Measurement Trains:

 the Challenges o...Highly Accurate Alignment of Data from Measurement Trains:

 the Challenges o...
Highly Accurate Alignment of Data from Measurement Trains:

 the Challenges o...Geoff Ballinger
 
Life in the Fast Lane: A Line-Rate Linear Road
Life in the Fast Lane: A Line-Rate Linear RoadLife in the Fast Lane: A Line-Rate Linear Road
Life in the Fast Lane: A Line-Rate Linear RoadAJAY KHARAT
 
Smart Traveller- Proficient Taxi Business Application
Smart Traveller- Proficient Taxi Business ApplicationSmart Traveller- Proficient Taxi Business Application
Smart Traveller- Proficient Taxi Business ApplicationGaurav Kumbhar
 
Resume_Jin_Q_2016_August_2page
Resume_Jin_Q_2016_August_2pageResume_Jin_Q_2016_August_2page
Resume_Jin_Q_2016_August_2pageLingqiu Jin
 
Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...
Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...
Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...ivaderivader
 
Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...
Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...
Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...ivaderivader
 
Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network
Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion NetworkTraffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network
Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Networkivaderivader
 
Automobile Route Matching with Dynamic Time Warping Using PySpark with Cather...
Automobile Route Matching with Dynamic Time Warping Using PySpark with Cather...Automobile Route Matching with Dynamic Time Warping Using PySpark with Cather...
Automobile Route Matching with Dynamic Time Warping Using PySpark with Cather...Databricks
 
Christian jensen advanced routing in spatial networks using big data
Christian jensen advanced routing in spatial networks using big dataChristian jensen advanced routing in spatial networks using big data
Christian jensen advanced routing in spatial networks using big datajins0618
 
Robotics:The computational motion planning:: Sampling based algorithms
Robotics:The computational motion planning:: Sampling based algorithmsRobotics:The computational motion planning:: Sampling based algorithms
Robotics:The computational motion planning:: Sampling based algorithmsPRAVEENTALARI4
 
A Multiobjective Evolutionary Algorithm for Infrastructure Location in Vehicu...
A Multiobjective Evolutionary Algorithm for Infrastructure Location in Vehicu...A Multiobjective Evolutionary Algorithm for Infrastructure Location in Vehicu...
A Multiobjective Evolutionary Algorithm for Infrastructure Location in Vehicu...Jamal Toutouh, PhD
 

Similar a Neural Approximate Dynamic Programming for On-Demand Ride-Pooling (20)

PRM-RL: Long-range Robotics Navigation Tasks by Combining Reinforcement Learn...
PRM-RL: Long-range Robotics Navigation Tasks by Combining Reinforcement Learn...PRM-RL: Long-range Robotics Navigation Tasks by Combining Reinforcement Learn...
PRM-RL: Long-range Robotics Navigation Tasks by Combining Reinforcement Learn...
 
Driving Behavior for ADAS and Autonomous Driving IV
Driving Behavior for ADAS and Autonomous Driving IVDriving Behavior for ADAS and Autonomous Driving IV
Driving Behavior for ADAS and Autonomous Driving IV
 
Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...
Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...
Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...
 
APRICOT 2017: Trafficshifting: Avoiding Disasters & Improving Performance at ...
APRICOT 2017: Trafficshifting: Avoiding Disasters & Improving Performance at ...APRICOT 2017: Trafficshifting: Avoiding Disasters & Improving Performance at ...
APRICOT 2017: Trafficshifting: Avoiding Disasters & Improving Performance at ...
 
Trafficshifting: Avoiding Disasters & Improving Performance at Scale
Trafficshifting: Avoiding Disasters & Improving Performance at ScaleTrafficshifting: Avoiding Disasters & Improving Performance at Scale
Trafficshifting: Avoiding Disasters & Improving Performance at Scale
 
Driving Behavior for ADAS and Autonomous Driving V
Driving Behavior for ADAS and Autonomous Driving VDriving Behavior for ADAS and Autonomous Driving V
Driving Behavior for ADAS and Autonomous Driving V
 
A Dynamic Logistic Dispatching System With Set-Based Particle Swarm Optimization
A Dynamic Logistic Dispatching System With Set-Based Particle Swarm OptimizationA Dynamic Logistic Dispatching System With Set-Based Particle Swarm Optimization
A Dynamic Logistic Dispatching System With Set-Based Particle Swarm Optimization
 
MSCV Capstone Spring 2020 Presentation - RL for AD
MSCV Capstone Spring 2020 Presentation - RL for ADMSCV Capstone Spring 2020 Presentation - RL for AD
MSCV Capstone Spring 2020 Presentation - RL for AD
 
Towards Auto-Extracting Car Park Structures: Image Processing Approach on Low...
Towards Auto-Extracting Car Park Structures: Image Processing Approach on Low...Towards Auto-Extracting Car Park Structures: Image Processing Approach on Low...
Towards Auto-Extracting Car Park Structures: Image Processing Approach on Low...
 
Highly Accurate Alignment of Data from Measurement Trains:

 the Challenges o...
Highly Accurate Alignment of Data from Measurement Trains:

 the Challenges o...Highly Accurate Alignment of Data from Measurement Trains:

 the Challenges o...
Highly Accurate Alignment of Data from Measurement Trains:

 the Challenges o...
 
Life in the Fast Lane: A Line-Rate Linear Road
Life in the Fast Lane: A Line-Rate Linear RoadLife in the Fast Lane: A Line-Rate Linear Road
Life in the Fast Lane: A Line-Rate Linear Road
 
Smart Traveller- Proficient Taxi Business Application
Smart Traveller- Proficient Taxi Business ApplicationSmart Traveller- Proficient Taxi Business Application
Smart Traveller- Proficient Taxi Business Application
 
Resume_Jin_Q_2016_August_2page
Resume_Jin_Q_2016_August_2pageResume_Jin_Q_2016_August_2page
Resume_Jin_Q_2016_August_2page
 
Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...
Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...
Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...
 
Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...
Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...
Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...
 
Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network
Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion NetworkTraffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network
Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network
 
Automobile Route Matching with Dynamic Time Warping Using PySpark with Cather...
Automobile Route Matching with Dynamic Time Warping Using PySpark with Cather...Automobile Route Matching with Dynamic Time Warping Using PySpark with Cather...
Automobile Route Matching with Dynamic Time Warping Using PySpark with Cather...
 
Christian jensen advanced routing in spatial networks using big data
Christian jensen advanced routing in spatial networks using big dataChristian jensen advanced routing in spatial networks using big data
Christian jensen advanced routing in spatial networks using big data
 
Robotics:The computational motion planning:: Sampling based algorithms
Robotics:The computational motion planning:: Sampling based algorithmsRobotics:The computational motion planning:: Sampling based algorithms
Robotics:The computational motion planning:: Sampling based algorithms
 
A Multiobjective Evolutionary Algorithm for Infrastructure Location in Vehicu...
A Multiobjective Evolutionary Algorithm for Infrastructure Location in Vehicu...A Multiobjective Evolutionary Algorithm for Infrastructure Location in Vehicu...
A Multiobjective Evolutionary Algorithm for Infrastructure Location in Vehicu...
 

Más de ivaderivader

DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
DDGK: Learning Graph Representations for Deep Divergence Graph KernelsDDGK: Learning Graph Representations for Deep Divergence Graph Kernels
DDGK: Learning Graph Representations for Deep Divergence Graph Kernelsivaderivader
 
So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality
So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality
So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality ivaderivader
 
Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...
Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...
Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...ivaderivader
 
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...ivaderivader
 
A Style-Based Generator Architecture for Generative Adversarial Networks
A Style-Based Generator Architecture for Generative Adversarial NetworksA Style-Based Generator Architecture for Generative Adversarial Networks
A Style-Based Generator Architecture for Generative Adversarial Networksivaderivader
 
CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...
CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...
CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...ivaderivader
 
Perception! Immersion! Empowerment! Superpowers as Inspiration for Visualization
Perception! Immersion! Empowerment! Superpowers as Inspiration for VisualizationPerception! Immersion! Empowerment! Superpowers as Inspiration for Visualization
Perception! Immersion! Empowerment! Superpowers as Inspiration for Visualizationivaderivader
 
StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...
StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...
StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...ivaderivader
 
Bad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTube
Bad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTubeBad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTube
Bad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTubeivaderivader
 
Invertible Denoising Network: A Light Solution for Real Noise Removal
Invertible Denoising Network: A Light Solution for Real Noise RemovalInvertible Denoising Network: A Light Solution for Real Noise Removal
Invertible Denoising Network: A Light Solution for Real Noise Removalivaderivader
 
Traffic Demand Prediction Based Dynamic Transition Convolutional Neural Network
Traffic Demand Prediction Based Dynamic Transition Convolutional Neural NetworkTraffic Demand Prediction Based Dynamic Transition Convolutional Neural Network
Traffic Demand Prediction Based Dynamic Transition Convolutional Neural Networkivaderivader
 
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training  MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training ivaderivader
 
Screen2Vec: Semantic Embedding of GUI Screens and GUI Components
Screen2Vec: Semantic Embedding of GUI Screens and GUI ComponentsScreen2Vec: Semantic Embedding of GUI Screens and GUI Components
Screen2Vec: Semantic Embedding of GUI Screens and GUI Componentsivaderivader
 
Natural Language to Visualization by Neural Machine Translation
Natural Language to Visualization by Neural Machine TranslationNatural Language to Visualization by Neural Machine Translation
Natural Language to Visualization by Neural Machine Translationivaderivader
 
Recommending What Video to Watch Next: A Multitask Ranking System
Recommending What Video to Watch Next: A Multitask Ranking SystemRecommending What Video to Watch Next: A Multitask Ranking System
Recommending What Video to Watch Next: A Multitask Ranking Systemivaderivader
 
Video Background Music Generation with Controllable Music Transformer
Video Background Music Generation with Controllable Music TransformerVideo Background Music Generation with Controllable Music Transformer
Video Background Music Generation with Controllable Music Transformerivaderivader
 
Spacewalker: Rapid UI Design Exploration Using Lightweight Markup Enhancement...
Spacewalker: Rapid UI Design Exploration Using Lightweight Markup Enhancement...Spacewalker: Rapid UI Design Exploration Using Lightweight Markup Enhancement...
Spacewalker: Rapid UI Design Exploration Using Lightweight Markup Enhancement...ivaderivader
 
Exploring Text Revision with Backspace and Caret in Virtual Reality
Exploring Text Revision with Backspace and Caret in Virtual RealityExploring Text Revision with Backspace and Caret in Virtual Reality
Exploring Text Revision with Backspace and Caret in Virtual Realityivaderivader
 

Más de ivaderivader (20)

Argument Mining
Argument MiningArgument Mining
Argument Mining
 
Papers at CHI23
Papers at CHI23Papers at CHI23
Papers at CHI23
 
DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
DDGK: Learning Graph Representations for Deep Divergence Graph KernelsDDGK: Learning Graph Representations for Deep Divergence Graph Kernels
DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
 
So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality
So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality
So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality
 
Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...
Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...
Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...
 
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...
 
A Style-Based Generator Architecture for Generative Adversarial Networks
A Style-Based Generator Architecture for Generative Adversarial NetworksA Style-Based Generator Architecture for Generative Adversarial Networks
A Style-Based Generator Architecture for Generative Adversarial Networks
 
CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...
CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...
CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...
 
Perception! Immersion! Empowerment! Superpowers as Inspiration for Visualization
Perception! Immersion! Empowerment! Superpowers as Inspiration for VisualizationPerception! Immersion! Empowerment! Superpowers as Inspiration for Visualization
Perception! Immersion! Empowerment! Superpowers as Inspiration for Visualization
 
StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...
StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...
StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...
 
Bad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTube
Bad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTubeBad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTube
Bad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTube
 
Invertible Denoising Network: A Light Solution for Real Noise Removal
Invertible Denoising Network: A Light Solution for Real Noise RemovalInvertible Denoising Network: A Light Solution for Real Noise Removal
Invertible Denoising Network: A Light Solution for Real Noise Removal
 
Traffic Demand Prediction Based Dynamic Transition Convolutional Neural Network
Traffic Demand Prediction Based Dynamic Transition Convolutional Neural NetworkTraffic Demand Prediction Based Dynamic Transition Convolutional Neural Network
Traffic Demand Prediction Based Dynamic Transition Convolutional Neural Network
 
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training  MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
 
Screen2Vec: Semantic Embedding of GUI Screens and GUI Components
Screen2Vec: Semantic Embedding of GUI Screens and GUI ComponentsScreen2Vec: Semantic Embedding of GUI Screens and GUI Components
Screen2Vec: Semantic Embedding of GUI Screens and GUI Components
 
Natural Language to Visualization by Neural Machine Translation
Natural Language to Visualization by Neural Machine TranslationNatural Language to Visualization by Neural Machine Translation
Natural Language to Visualization by Neural Machine Translation
 
Recommending What Video to Watch Next: A Multitask Ranking System
Recommending What Video to Watch Next: A Multitask Ranking SystemRecommending What Video to Watch Next: A Multitask Ranking System
Recommending What Video to Watch Next: A Multitask Ranking System
 
Video Background Music Generation with Controllable Music Transformer
Video Background Music Generation with Controllable Music TransformerVideo Background Music Generation with Controllable Music Transformer
Video Background Music Generation with Controllable Music Transformer
 
Spacewalker: Rapid UI Design Exploration Using Lightweight Markup Enhancement...
Spacewalker: Rapid UI Design Exploration Using Lightweight Markup Enhancement...Spacewalker: Rapid UI Design Exploration Using Lightweight Markup Enhancement...
Spacewalker: Rapid UI Design Exploration Using Lightweight Markup Enhancement...
 
Exploring Text Revision with Backspace and Caret in Virtual Reality
Exploring Text Revision with Backspace and Caret in Virtual RealityExploring Text Revision with Backspace and Caret in Virtual Reality
Exploring Text Revision with Backspace and Caret in Virtual Reality
 

Último

Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...Zilliz
 
Vector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxVector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxRemote DBA Services
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Orbitshub
 
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...apidays
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Jeffrey Haguewood
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...apidays
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...apidays
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingEdi Saputra
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdfSandro Moreira
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...Zilliz
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...apidays
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistandanishmna97
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native ApplicationsWSO2
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWERMadyBayot
 
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Angeliki Cooney
 
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 AmsterdamDEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 AmsterdamUiPathCommunity
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfOrbitshub
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodJuan lago vázquez
 

Último (20)

Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
 
Vector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxVector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptx
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
 
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistan
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
 
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
 
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 AmsterdamDEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 

Neural Approximate Dynamic Programming for On-Demand Ride-Pooling

  • 1. 2022.03.18 Neural Approximate Dynamic Programming for On-Demand Ride-Pooling Sanket Shah, Meghna Lowalekar, Pradeep Varakantham AAAI ’19 Hongkyu Lim
  • 2. Contents • Introduction • Background • Ride-pool Matching Problem(RMP) • NeurADP: Neural Approximate Dynamic Programming • Experiment • Results
  • 3. 3 Introduction • On-Demand Ride- Pooling Unlike Taxi-on-Demand (ToD) • Benefits a) Reducing costs b) Making more money per trip c) Covering more # of passengers with the same or less # of cars • Ride-Pool Matching Problem(RMP) • Markov Decision Process • Approximate Dynamic Programming(ADP) • Integer Linear Program(ILP) • Deep Reinforcement Learning (Use of Neural Network in approximating value function by connecting it to Reinforcement Learning)
  • 4. 4 Introduction 1) Relying on the traditional planning approaches to model the RMP • It does not scale to on-demand city-scale scenarios. 2) Greedy search mechanism • It does not consider the impact of a given assignment on future assignments. 3) Reinforcement Learning to address myopic assignments • It cannot be extended to deal with the task when vehicles get more than one passenger at a time. 4) Approximate Dynamic Programming framework to solve the ToD problem • Linear Program does not hold for the RMP with arbitrary vehicle capacities. • Current ADP does not consider cases in which vehicles are already partially filled with prior passengers. The constraints the researchers ran into in the past 😫
  • 5. 5 Introduction 1) Arbitrary capacity RMP problem as an ADP 2) Proposign Neural ADP(NeurADP) • A general ADP method that can learn value functions. (approximated using Neural Networks) from ILP based assignment problems. 3) Bring techniques from Deep Q-Networks to improve the stability and scalability of NeurADP Contributions 🥴
  • 6. 6 Background 1) A framework based on Markov Decision Process(MDP) model  ADP tackles large multi-period stochastic fleet optimization problems. Approximate Dynamic Programming(ADP) • MDP : • ADP :
  • 7. 7 Ride-pool Matching Problem (RMP) 1) Passenger Fleet matching algorithm  Consider a fleet of vehicles with Random initial locations. How to serve requests with the provided number of vehicles? • 𝒢 ∶ Road Network. (ℒ, ℰ) (set of street intersections ,adjacency of intersections) • 𝒰 ∶ Combination of requests • ℛ ∶ Vehicles or resources • 𝒟 ∶ Set of constraints on delay  {𝜏, 𝜆} • Δ ∶ Decision epoch duration • 𝒪 : Objective  Number of Car-pooling cases
  • 8. 8 NeurADP <Schematic outlining overall NeurADP> Neural Approximate Dynamic Programming (NeurADP)
  • 9. 9 NeurADP <Steps> A. Get requests based on NYC Taxi dataset B. Map the requests and their combinations to vehicles 1) Vehicles serve them under the constraints defined by 𝒟 to create feasible actions C. Score each of these feasible actions using Neural Network Value Function Neural Approximate Dynamic Programming (NeurADP)
  • 10. 10 NeurADP <Steps> D. Create a mapping of requests to vehicles that maximises the sum of scores generated in (C) using the Integer Linear Program(ILP) E. Use this final mapping to update the score function F. Simulate the motion of vehicles until the next epoch Neural Approximate Dynamic Programming (NeurADP)
  • 11. 11 NeurADP • 1 to 1 mapping for ToD is a simple task operated in Linear Programming. • However, many to 1 mapping is hard. • 2 cases • Single empty vehicle • Partially filled vehicle • The task needs to be solved with respect to unexpected occurrences. • It cannot be solved with Linear Programming. Approximate Dynamic Programming(ADP)
  • 12. 12 NeurADP • Past work in ADP for ToD uses the dual values to update the parameters of their value function approximation. • The best action in optimizing RMP is to apply Integer Linear Program(ILP) • ILP has bad LP-relaxations • We cannot use LP-dual to update our value function. • Consequently, we connect ADP to Reinforcement Learning. • Use the more general Bellman update to optimize the value function. No more LP-duals
  • 13. 13 NeurADP • Past work in ADP addresses high dimensionality by hand-crafted attributes(ex. Aggregated number of vehicles in each location.) • It’s okay… for ToD because it is one-to-one mapping. • However, how about RMP? • Each vehicle has different number of passengers going to multiple different locations… • Use Neural Network based value function to automatically learn a compact low dimensional representation of the large state space. Curse of Dimensionality 😵💫
  • 14. 14 NeurADP • Naïve approaches to approximating Neural Network value functions in Deep Reinforcement Learning is unstable. • Replace LP-duals with more general Bellman update for stepping up the Neural Network value function • It’s named “Neural ADP”. 🥴 Challenges of learning a Neural Network value function
  • 15. 15 NeurADP • 2 Steps for constraints 1. Constraints at the vehicle level  Satisfying delay constraints 𝒟 and vehicle capacity constraints 2. Constraints at the system level  Each request is assigned to at most one vehicle. How to handle exponential action space?
  • 16. 16 Experiments • Setting up the constraints • The maximum allowed waiting time 𝜏 : 120 - 420 seconds • The number of vehicles ℛ : 1000 - 3000 • Capacity : 2 – 10 passengers • The value of maximum allowable detour delay 𝜆 : 2 * 𝜏 • The decision epoch duration Δ : 60 seconds • Baselines • ZAC algorithm • TBF-Complete by Lowalekar et. al. • TBF-Heuristic by the author’s group Comparing the performance of NeurADP to leading approaches for solving RMP
  • 17. 17 Experiments • Dataset • New York Yellow Taxi Dataset 2016 • Road network : osmnx with ‘drive’ network type • In total, 4373 nodes & 9540 edges • Manhattan only • Pickup time is converted to approximate decision epoch based on Δ. • On average, 322,714 requests in a day • 19820 requests during peak hour Comparing the performance of NeurADP to leading approaches for solving RMP
  • 18. 18 Results • Dataset • New York Yellow Taxi Dataset 2016 • Road network : osmnx with ‘drive’ network type • In total, 4373 nodes & 9540 edges • Manhattan only • Pickup time is converted to approximate decision epoch based on Δ. • On average, 322,714 requests in a day • 19820 requests during peak hour The goal is to serve more requests trying not to be too greedy. 🥴
  • 19. 19 Results The goal is to serve more requests trying not to be too greedy. 🥴🥴 ❗️😵
  • 20. 20 Results The constraints might affect the result? 🥴
  • 21. 21 Results The constraints might affect the result? Effect of changing the tolerance to delay, 𝜏 • The lower 𝜏 makes it difficult to accept new requests •  It’s more important to consider future requests when 𝜏 is lower.
  • 22. 22 Results The constraints might affect the result? Effect of changing the capacity • The higher capacity a vehicle has, the larger scope for improvement of the system along with the future requests is taken into account.
  • 23. 23 Results The constraints might affect the result? Effect of changing the number of vehicles • The quality of assignments plays a smaller role because there will always be a vehicle to serve the request.