SlideShare una empresa de Scribd logo
1 de 72
Deliberately Planning and Acting for Angry Birds with
Refinement Methods
Ruofei Du, Zebao Gao, Zheng Xu
CMSC 722 Technical Report advised by Prof. Nau & Dr. Shivashankar
Computer Science Dept., Univ. of Maryland, College Park
Introduction
Angry Birds
Introduction
Angry Birds
200 Million
Introduction
Angry Birds
Introduction
Angry Birds
Introduction
Angry Birds
Birds
Introduction
Angry Birds
Slingshot
Introduction
Angry Birds
Pig
s
Introduction
Angry Birds
Introduction
Angry Birds
Introduction
Angry Birds
Related Work
Planning & Machine Learning
Related Work
Planning & Machine Learning
Related Work
Planning & Machine Learning
Related Work
Planning & Machine Learning
Related Work
Planning & Machine Learning
Related Work
Planning & Machine Learning
Related Work
Planning & Machine Learning
Most work focuses on
modeling the physical properties of the game or
utilize machines learning as empirical knowledge base.
None of the related work
compares the methods
using or not using refinements methods
in an ARP-interleave framework.
Contribution
Sample log of our system
0 [System] Program starts with configuration -d
32 [System] Server waiting on port: 9000
1051 [System] Client connected
1934 [System] Running A* agent without IRPE
8309 [Vision] Detecting objects in the Angry Birds using vision
module
10068 [Vision] Detect TNTs 0
10069 [Vision] Detect pigs and rolling 1, glass 5, stone 1, wood
27, birds 8
10069 [Vision] Statistics: 1, 34, 0
10213 [Planner] m1-destroyAllPigs: 1 pigs
10216 [Planner] m2-destroyPig
ab.vision.ABObject[x=536,y=290,width=14,height=10]
10216 [Planner] Estimate launch point from 2
10217 [Planner] launch point java.awt.Point[x=9,y=961], angle
73.79194556203768
17742 [Actor] Shooting starts 193, 328, -184, 633
27765 [Actor] Shooting completes
28096 [Vision] Scale factor = 1.0006048459391437
28267 [Vision] Detecting objects in the Angry Birds using vision
module
28943 [Vision] Detect TNTs 0
28944 [Vision] Detect pigs and rolling 0, glass 2, stone 1, wood
10, birds2
28944 [Vision] Statistics: 0, 13, 0
29116 [Planner] m1-destroyAllPigs: 1 pigs
29116 [Planner] m2-destroyPig
ab.vision.ABObject[x=536,y=290,width=14,height=10]
29117 [Planner] Estimate launch point from 2
29117 [Planner] launch point java.awt.Point[x=0,y=959], angle
72.99302990476194
36778 [Actor] no sling detected, can not execute the shot, will
re-segement the image
37049 [Vision] Detecting objects in the Angry Birds using vision
module
38198 [Vision] Detect TNTs 0
Design and Implementation of
Greedy, DFFS, A* specifically
for solving Angry Birds puzzles
Design a Refinement Acting Engine (RAE)
Based on ARP-interleave
With Sequential Refinement Planning Engine (SeRPE)
Evaluation and Comparison amongst
3 algorithms in 2 conditions
Greedy / DFFS / A* && Planning Only / SeRPE
Discussion, illustration and insights from
Integrating Planning and Acting
Using refinement methods for Angry Birds
Angry Bird Platform
Rebuilt upon Ge et al., 2014
Figure by our team
Formalism
State Variable Representation
Formalism
State Variable Representation
The angry birds platform could
execute the following commands
Formalism
Commands and Tasks
findMBR()
perceive all the minimum bounding
rectangles (MBR) of Objects in the current
state
estimateLauchPoint(sl, target)
estimate the Start Points
used to shoot bird from the Sling and the target Point
shot(b, start)
shot a bird by pulling it to the start point
isReachable(sl, start, target)
estimate if the Target Point is reachable based on the
Start Point, or the Target is blocked by Obstacles
getSupporters(obj)
get all the objects that suppot the object
We define the following commands
that are executable in the program
getMBR(obj)
getHitPoint(obj)
isBlocked(obj)
getAllPigs()
getAllBirds()
getCurrentBird()
getTNTs()
getObstacles(obj)
estimateScoreOfObjs(objs)
We define the following tasks
destroyAllPigs()
chooseTarget()
estimateScore(p)
destroy(obj)
destroy(obj, b)
hit(b, obj)
Refinement method
m-destroyAllPigs()
m1-chooseTarget()
m2-chooseTarget()
m1-selectTarget()
m2-selectTarget()
m1-destroyTarget(t)
m2-destroyTarget(p)
m1-destroyPig(p, b)
m1-hit(a, obj)
m2-hit(a, obj)
m3-hit(a, obj)
m4-hit(a, obj)
Refinement Tree
Challenge
World is seldom predictable
(Ghallab, Nau and Traverso, 2015)
Actions failures
A shot may not accomplish the goal of destroying a
targeted pig
Challenge
World is seldom predictable
(Ghallab, Nau and Traverso, 2015)
Unexpected side effects of
actions
A shot may changing the future planning state by
destroying other pigs
Challenge
World is seldom predictable
(Ghallab, Nau and Traverso, 2015)
Exogenous events
A shot may put the stage into an unsolvable state like
surrounding a pig with irons
Challenge
World is seldom predictable
(Ghallab, Nau and Traverso, 2015)
ARP-interleave
(Ghallab, Nau and Traverso, 2015)
1. Before each step:
Generate a plan based on the SeRPE
refinement tree.
ARP-interleave
(Ghallab, Nau and Traverso, 2015)
2. After each step:
Update information of the world
(outcomes, objects)
ARP-interleave
(Ghallab, Nau and Traverso, 2015)
3. If the current step fails:
try remaining methods
It models the problem more
accurately
Advantages
ARP-interleave Framework
Plans generated by this system
are more practical
the actual status of the world are always taken into
consideration
Advantages
ARP-interleave Framework
Better decision
can be made about choosing the next plan..
Advantages
ARP-interleave Framework
Search algorithms for
nondeterministic choice in SeRPE
SeRPE-Greedy
Two heuristics:
1. always choose an existing pig
as target
2. choose the pig that is closest to
the sling
SeRPE-DFFS
1 Heuristic:
always choose an existing pig as target
Impl:
maintain visited states in a HashSet
SeRPE-A*
Experiment
Nvidia Quadro K6000
Experiment
Intel Xeon CPU E5-2667 2.90GHz
32GB RAM
Experiment
Chrome Version of Angry Birds
chrome.angrybirds.com
Experiment
Chrome Version of Angry Birds
chrome.angrybirds.com
Dataset
Statistics
Dataset
Highest Score for Each Level
Dataset
Average Time Cost for Each Level
(ms)
Results
SeRPE-A* outperforms both in
highest score and time cost
Why deterministic
models are worse? /
Why SeRPE with A* is
better?
Inaccurate Simulation
It is a challenging task to derive an exact model of a physical world.
The knowledge base of the physical world is built upon the prior
exploration with trials and errors. Even in a virtual world like Angry
Birds, it is almost impossible to model the world without reading its
source code.
Discussion
Why deterministic model fails
(Ghallab, Nau and Traverso, 2015)
Changes in Time
In practical scenarios like Angry Birds, the global states of any
object may be subject to change from time to time. For example,
it is very hard to know whether the scene is static or not after a
shot. The structure may be unstable and moving in a very slow
pace. As a result, the subtle changes in the global states may
lead to failure of the current plan.
Discussion
Why deterministic model fails
(Ghallab, Nau and Traverso, 2015)
Erroneous Actions
As for human beings, it is hard to perform an action such as
textit{move left hand 5 centimeters forward exactly}. Similarly,
for a video game like Angry Birds that involves human
interactions, the acting engine hardly points to the perfect
position in pixel-level. Consequently, the actor may produce
different states than the planner predicted.
Discussion
Why deterministic model fails
(Ghallab, Nau and Traverso, 2015)
1. present a deliberately planning and acting system
with refinement methods for the popular Angry
Birds video game.
2. design a RAE based on ARP-interleave with
SeRPE. Greedy, DFFS and A* are incorporated to
search for planning
3. our experimental results show that ARP-interleave
outperforms their counterparts which purely rely
on the search algorithms
Conclusion
Summary
Deliberately Planning and Acting for Angry Birds with
Refinement Methods
Ruofei Du, Zebao Gao, Zheng Xu
CMSC 722 Technical Report advised by Prof. Nau & Dr. Shivashankar
Computer Science Dept., Univ. of Maryland, College Park
Thank
you!
Introduction
Angry Birds

Más contenido relacionado

Similar a Deliberately Planning and Acting for Angry Birds with Refinement Methods

Slope one recommender on hadoop
Slope one recommender on hadoopSlope one recommender on hadoop
Slope one recommender on hadoopYONG ZHENG
 
Futebol Robótico: A Ciência para além do Futebol (Pedro Lima)
Futebol Robótico: A Ciência para além do Futebol (Pedro Lima)Futebol Robótico: A Ciência para além do Futebol (Pedro Lima)
Futebol Robótico: A Ciência para além do Futebol (Pedro Lima)maquina.especulativa
 
Atari Game State Representation using Convolutional Neural Networks
Atari Game State Representation using Convolutional Neural NetworksAtari Game State Representation using Convolutional Neural Networks
Atari Game State Representation using Convolutional Neural Networksjohnstamford
 
Dr.Kawewong Ph.D Thesis
Dr.Kawewong Ph.D ThesisDr.Kawewong Ph.D Thesis
Dr.Kawewong Ph.D ThesisSOINN Inc.
 
Henrik Christensen - Vision for co-robot applications
Henrik Christensen  -  Vision for co-robot applicationsHenrik Christensen  -  Vision for co-robot applications
Henrik Christensen - Vision for co-robot applicationsDaniel Huber
 
Henrik Christensen - Vision for Co-robot Applications
Henrik Christensen - Vision for Co-robot ApplicationsHenrik Christensen - Vision for Co-robot Applications
Henrik Christensen - Vision for Co-robot ApplicationsDaniel Huber
 
Operationalizing Clojure Confidently
Operationalizing Clojure ConfidentlyOperationalizing Clojure Confidently
Operationalizing Clojure ConfidentlyPrasanna Gautam
 
Visibility Optimization for Games
Visibility Optimization for GamesVisibility Optimization for Games
Visibility Optimization for GamesUmbra
 
Visibility Optimization for Games
Visibility Optimization for GamesVisibility Optimization for Games
Visibility Optimization for GamesSampo Lappalainen
 
Ray: A Cluster Computing Engine for Reinforcement Learning Applications with ...
Ray: A Cluster Computing Engine for Reinforcement Learning Applications with ...Ray: A Cluster Computing Engine for Reinforcement Learning Applications with ...
Ray: A Cluster Computing Engine for Reinforcement Learning Applications with ...Databricks
 
Machine Learning Exposed - James Weaver - Codemotion Amsterdam 2017
Machine Learning Exposed - James Weaver - Codemotion Amsterdam 2017Machine Learning Exposed - James Weaver - Codemotion Amsterdam 2017
Machine Learning Exposed - James Weaver - Codemotion Amsterdam 2017Codemotion
 
Real-time Moving Object Detection using SURF
Real-time Moving Object Detection using SURFReal-time Moving Object Detection using SURF
Real-time Moving Object Detection using SURFiosrjce
 
Navigational BCI Using Acoustic Stimulation
Navigational BCI Using Acoustic StimulationNavigational BCI Using Acoustic Stimulation
Navigational BCI Using Acoustic Stimulationwacax
 
IRJET Autonomous Simultaneous Localization and Mapping
IRJET  	  Autonomous Simultaneous Localization and MappingIRJET  	  Autonomous Simultaneous Localization and Mapping
IRJET Autonomous Simultaneous Localization and MappingIRJET Journal
 
Online learning & adaptive game playing
Online learning & adaptive game playingOnline learning & adaptive game playing
Online learning & adaptive game playingSaeid Ghafouri
 
Flow Trajectory Approach for Human Action Recognition
Flow Trajectory Approach for Human Action RecognitionFlow Trajectory Approach for Human Action Recognition
Flow Trajectory Approach for Human Action RecognitionIRJET Journal
 
OpenGL L02-Transformations
OpenGL L02-TransformationsOpenGL L02-Transformations
OpenGL L02-TransformationsMohammad Shaker
 

Similar a Deliberately Planning and Acting for Angry Birds with Refinement Methods (20)

Slope one recommender on hadoop
Slope one recommender on hadoopSlope one recommender on hadoop
Slope one recommender on hadoop
 
report
reportreport
report
 
Futebol Robótico: A Ciência para além do Futebol (Pedro Lima)
Futebol Robótico: A Ciência para além do Futebol (Pedro Lima)Futebol Robótico: A Ciência para além do Futebol (Pedro Lima)
Futebol Robótico: A Ciência para além do Futebol (Pedro Lima)
 
Atari Game State Representation using Convolutional Neural Networks
Atari Game State Representation using Convolutional Neural NetworksAtari Game State Representation using Convolutional Neural Networks
Atari Game State Representation using Convolutional Neural Networks
 
Dr.Kawewong Ph.D Thesis
Dr.Kawewong Ph.D ThesisDr.Kawewong Ph.D Thesis
Dr.Kawewong Ph.D Thesis
 
Henrik Christensen - Vision for co-robot applications
Henrik Christensen  -  Vision for co-robot applicationsHenrik Christensen  -  Vision for co-robot applications
Henrik Christensen - Vision for co-robot applications
 
Henrik Christensen - Vision for Co-robot Applications
Henrik Christensen - Vision for Co-robot ApplicationsHenrik Christensen - Vision for Co-robot Applications
Henrik Christensen - Vision for Co-robot Applications
 
Operationalizing Clojure Confidently
Operationalizing Clojure ConfidentlyOperationalizing Clojure Confidently
Operationalizing Clojure Confidently
 
Visibility Optimization for Games
Visibility Optimization for GamesVisibility Optimization for Games
Visibility Optimization for Games
 
Visibility Optimization for Games
Visibility Optimization for GamesVisibility Optimization for Games
Visibility Optimization for Games
 
Eyes or heart
Eyes or heartEyes or heart
Eyes or heart
 
Ray: A Cluster Computing Engine for Reinforcement Learning Applications with ...
Ray: A Cluster Computing Engine for Reinforcement Learning Applications with ...Ray: A Cluster Computing Engine for Reinforcement Learning Applications with ...
Ray: A Cluster Computing Engine for Reinforcement Learning Applications with ...
 
Machine Learning Exposed - James Weaver - Codemotion Amsterdam 2017
Machine Learning Exposed - James Weaver - Codemotion Amsterdam 2017Machine Learning Exposed - James Weaver - Codemotion Amsterdam 2017
Machine Learning Exposed - James Weaver - Codemotion Amsterdam 2017
 
J017377578
J017377578J017377578
J017377578
 
Real-time Moving Object Detection using SURF
Real-time Moving Object Detection using SURFReal-time Moving Object Detection using SURF
Real-time Moving Object Detection using SURF
 
Navigational BCI Using Acoustic Stimulation
Navigational BCI Using Acoustic StimulationNavigational BCI Using Acoustic Stimulation
Navigational BCI Using Acoustic Stimulation
 
IRJET Autonomous Simultaneous Localization and Mapping
IRJET  	  Autonomous Simultaneous Localization and MappingIRJET  	  Autonomous Simultaneous Localization and Mapping
IRJET Autonomous Simultaneous Localization and Mapping
 
Online learning & adaptive game playing
Online learning & adaptive game playingOnline learning & adaptive game playing
Online learning & adaptive game playing
 
Flow Trajectory Approach for Human Action Recognition
Flow Trajectory Approach for Human Action RecognitionFlow Trajectory Approach for Human Action Recognition
Flow Trajectory Approach for Human Action Recognition
 
OpenGL L02-Transformations
OpenGL L02-TransformationsOpenGL L02-Transformations
OpenGL L02-Transformations
 

Más de Ruofei Du

Project Geollery.com: Reconstructing a Live Mirrored World With Geotagged Soc...
Project Geollery.com: Reconstructing a Live Mirrored World With Geotagged Soc...Project Geollery.com: Reconstructing a Live Mirrored World With Geotagged Soc...
Project Geollery.com: Reconstructing a Live Mirrored World With Geotagged Soc...Ruofei Du
 
Geollery: A Mixed Reality Social Media Platform
Geollery: A Mixed Reality Social Media PlatformGeollery: A Mixed Reality Social Media Platform
Geollery: A Mixed Reality Social Media PlatformRuofei Du
 
Fusing Multimedia Data Into Dynamic Virtual Environments
Fusing Multimedia Data Into Dynamic Virtual EnvironmentsFusing Multimedia Data Into Dynamic Virtual Environments
Fusing Multimedia Data Into Dynamic Virtual EnvironmentsRuofei Du
 
Montage4D: Interactive Seamless Fusion of Multiview Video Textures
Montage4D: Interactive Seamless Fusion of Multiview Video TexturesMontage4D: Interactive Seamless Fusion of Multiview Video Textures
Montage4D: Interactive Seamless Fusion of Multiview Video TexturesRuofei Du
 
CTUAAA Summit 2017 Schedule
CTUAAA Summit 2017 ScheduleCTUAAA Summit 2017 Schedule
CTUAAA Summit 2017 ScheduleRuofei Du
 
交大历史与梅竹赛
交大历史与梅竹赛交大历史与梅竹赛
交大历史与梅竹赛Ruofei Du
 
Social Street View: Blending Immersive Street Views with Geo-tagged Social Media
Social Street View: Blending Immersive Street Views with Geo-tagged Social MediaSocial Street View: Blending Immersive Street Views with Geo-tagged Social Media
Social Street View: Blending Immersive Street Views with Geo-tagged Social MediaRuofei Du
 
Video Fields: Fusing Multiple Surveillance Videos into a Dynamic Virtual Envi...
Video Fields: Fusing Multiple Surveillance Videos into a Dynamic Virtual Envi...Video Fields: Fusing Multiple Surveillance Videos into a Dynamic Virtual Envi...
Video Fields: Fusing Multiple Surveillance Videos into a Dynamic Virtual Envi...Ruofei Du
 
Chinese Caligraphy 品读书法·感悟中华 (2010)
Chinese Caligraphy 品读书法·感悟中华 (2010)Chinese Caligraphy 品读书法·感悟中华 (2010)
Chinese Caligraphy 品读书法·感悟中华 (2010)Ruofei Du
 
Statistics for K-mer Based Splicing Analysis
Statistics for K-mer Based Splicing AnalysisStatistics for K-mer Based Splicing Analysis
Statistics for K-mer Based Splicing AnalysisRuofei Du
 
基于视频的疲劳驾驶检测系统
基于视频的疲劳驾驶检测系统基于视频的疲劳驾驶检测系统
基于视频的疲劳驾驶检测系统Ruofei Du
 
Online Vigilance Analysis Combining Video and Electrooculography Features
Online Vigilance Analysis Combining Video and Electrooculography FeaturesOnline Vigilance Analysis Combining Video and Electrooculography Features
Online Vigilance Analysis Combining Video and Electrooculography FeaturesRuofei Du
 

Más de Ruofei Du (12)

Project Geollery.com: Reconstructing a Live Mirrored World With Geotagged Soc...
Project Geollery.com: Reconstructing a Live Mirrored World With Geotagged Soc...Project Geollery.com: Reconstructing a Live Mirrored World With Geotagged Soc...
Project Geollery.com: Reconstructing a Live Mirrored World With Geotagged Soc...
 
Geollery: A Mixed Reality Social Media Platform
Geollery: A Mixed Reality Social Media PlatformGeollery: A Mixed Reality Social Media Platform
Geollery: A Mixed Reality Social Media Platform
 
Fusing Multimedia Data Into Dynamic Virtual Environments
Fusing Multimedia Data Into Dynamic Virtual EnvironmentsFusing Multimedia Data Into Dynamic Virtual Environments
Fusing Multimedia Data Into Dynamic Virtual Environments
 
Montage4D: Interactive Seamless Fusion of Multiview Video Textures
Montage4D: Interactive Seamless Fusion of Multiview Video TexturesMontage4D: Interactive Seamless Fusion of Multiview Video Textures
Montage4D: Interactive Seamless Fusion of Multiview Video Textures
 
CTUAAA Summit 2017 Schedule
CTUAAA Summit 2017 ScheduleCTUAAA Summit 2017 Schedule
CTUAAA Summit 2017 Schedule
 
交大历史与梅竹赛
交大历史与梅竹赛交大历史与梅竹赛
交大历史与梅竹赛
 
Social Street View: Blending Immersive Street Views with Geo-tagged Social Media
Social Street View: Blending Immersive Street Views with Geo-tagged Social MediaSocial Street View: Blending Immersive Street Views with Geo-tagged Social Media
Social Street View: Blending Immersive Street Views with Geo-tagged Social Media
 
Video Fields: Fusing Multiple Surveillance Videos into a Dynamic Virtual Envi...
Video Fields: Fusing Multiple Surveillance Videos into a Dynamic Virtual Envi...Video Fields: Fusing Multiple Surveillance Videos into a Dynamic Virtual Envi...
Video Fields: Fusing Multiple Surveillance Videos into a Dynamic Virtual Envi...
 
Chinese Caligraphy 品读书法·感悟中华 (2010)
Chinese Caligraphy 品读书法·感悟中华 (2010)Chinese Caligraphy 品读书法·感悟中华 (2010)
Chinese Caligraphy 品读书法·感悟中华 (2010)
 
Statistics for K-mer Based Splicing Analysis
Statistics for K-mer Based Splicing AnalysisStatistics for K-mer Based Splicing Analysis
Statistics for K-mer Based Splicing Analysis
 
基于视频的疲劳驾驶检测系统
基于视频的疲劳驾驶检测系统基于视频的疲劳驾驶检测系统
基于视频的疲劳驾驶检测系统
 
Online Vigilance Analysis Combining Video and Electrooculography Features
Online Vigilance Analysis Combining Video and Electrooculography FeaturesOnline Vigilance Analysis Combining Video and Electrooculography Features
Online Vigilance Analysis Combining Video and Electrooculography Features
 

Último

How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilV3cube
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoffsammart93
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProduct Anonymous
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobeapidays
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUK Journal
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century educationjfdjdjcjdnsjd
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slidevu2urc
 
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
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsJoaquim Jorge
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherRemote DBA Services
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
 

Último (20)

How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of Brazil
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
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...
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 

Deliberately Planning and Acting for Angry Birds with Refinement Methods

Notas del editor

  1. Good morning, everyone. My name is Ruofei. This is Zebao, this is Zheng. Our topic is “Deliberately Planning and Acting for Angry Birds with Refinement Methods”
  2. First of all, we’ll play our demo video for a quick overview of our project. https://www.youtube.com/watch?v=u7XJ0g6d9po
  3. Angry Birds is a popular video game by ROVIO in iOS, Android, PC, Mac and even on the web.
  4. It has attracted over 200 million players all over the world since 2009. Image credit: http://cdn2.hubspot.net/hub/202647/file-362198412-jpg/images/user_generated_content_is_the_future_of_ecommerce_2.jpg
  5. It has attracted over 200 million players all over the world since 2009.
  6. The task for the player is to shoot birds with different properties from a slingshot at a structure that houses pigs and to destroy all the pigs.
  7. The task for the player is to shoot birds with different properties from a slingshot at a structure that houses pigs and to destroy all the pigs.
  8. The task for the player is to shoot birds with different properties from a slingshot at a structure that houses pigs and to destroy all the pigs.
  9. The task for the player is to shoot birds with different properties from a slingshot at a structure that houses pigs and to destroy all the pigs.
  10. The structure can be very complicated and can involve a number of different object categories with different properties, such as wood, ice and stone, as shown in Fig. 1. After each shot, the entire game environment is subject to tremendous change.
  11. The structure can be very complicated and can involve a number of different object categories with different properties, such as wood, ice and stone, as shown in Fig. 1. After each shot, the entire game environment is subject to tremendous change.
  12. After each shot, the entire game environment is subject to tremendous change.
  13. One motivation of our work is to assist new players to play the game. The other motivation is from IJCAI Angry Birds competition, which is due in July.
  14. One motivation of our work is to assist new players to play the game. The other motivation is from IJCAI Angry Birds competition, which is due in July.
  15. Past research on Angry Birds has largely focus on AI Planning or Machine Learning, as well as geometrical representation and physical modeling.
  16. Past research on Angry Birds has largely focus on AI Planning or Machine Learning, as well as geometrical representation and physical modeling.
  17. Past research on Angry Birds has largely focus on AI Planning or Machine Learning, as well as geometrical representation and physical modeling.
  18. Past research on Angry Birds has largely focus on AI Planning or Machine Learning, as well as geometrical representation and physical modeling.
  19. Past research on Angry Birds has largely focus on AI Planning or Machine Learning, as well as geometrical representation and physical modeling.
  20. Past research on Angry Birds has largely focus on AI Planning or Machine Learning, as well as geometrical representation and physical modeling.
  21. However,
  22. Here we summarizes the contribution of our work as follows:
  23. First
  24. Second
  25. Third
  26. Eventually
  27. Here is framework figure by our team. First, there is a chrome extension to capture screenshot from the game. Next, the game server decoded the screenshot and transfers to the automatic agent, the client side. Finally, the client uses a vision module provided by the IJCAI community and uses our planner to calculate the interactions for the game. They also provides an actor module
  28. Zheng: Here is our problem formalism of the Angry Birds puzzles.
  29. The following state variables are kept up-to-date by the vision component of angry birds
  30. Eventually
  31. Eventually
  32. Eventually
  33. Eventually
  34. Eventually
  35. Eventually
  36. Eventually
  37. Eventually
  38. Eventually
  39. Eventually
  40. Eventually
  41. Eventually
  42. Eventually
  43. The following state variables are kept up-to-date by the vision component of angry birds
  44. Thanks Zheng for talking about problem formalism. So, One question we may have at this point is: What is difficult with Angry birds? What are the challenges? One of the biggest challenges is that the world is seldom predictable. Even a well-trained player cannot tell the exact states of all objects after a single shot.
  45. To be specific. First thing, a shot may not accomplish the goal of destroying a targeted pig.
  46. Also. Actions often have unexpected side effects. A shot may changing the future planning state by destroying other pigs.
  47. And Even worse. A shot may put the stage into an unsolvable state like surrounding a pig with irons.
  48. So, How are we dealing with this? We are applying a planning and acting approach, ARP-interleave, which will replan for next step after each action. Before each step, it will generate a plan based on the SeRPE refinement tree.
  49. After each step, the system will check the current status of the world. It will not only check the outcomes of the previous action. Also, it will update the status of all the objects (like pigs, stones, woods, etc.) according to their latest actual state.
  50. And If the current step fails to achieve the goal, the planner will try to use the remaining methods that are feasible in current state.
  51. ARP-interleave well fit the purpose of solving the Angry Birds problem. Here are its advantages. First, It models the problem more accurately
  52. Second, Plans generated by this system are more practical because the actual status of the world is always taken into consideration.
  53. Finally, as a result, better decisions can be made about choosing the next plan.
  54. Now let’s look at the search algorithms we are using to generate plans in the simulation process of SeRPE. We adopt three forward search algorithms in our implementation: greedy search, DFFS and A*. We’ll call these algorithms SePRE-Greedy,SePRE-DFFS and SePRE-A* respectively.
  55. SeRPE-Greedy uses two heuristics: The first heuristics always choose a pig as target. The second heuristics will choose the pig that is closest to the sling. In our planning and acting framework, simulation algorithm is called after each action. And if we are using the second heuristic, for example, then each time SeRPE-Greedy is called, it will return a plan that hits the pigs one by one in the order of distance.
  56. DFFS. One advantage of depth first search comparing with greedy search is that it guarantees to find a solution if one exists. SeRPE-DFFS uses one heuristic: always choose an existing pig as a target. In our implementation, we maintain a Hashset to keep the visited states.
  57. And finally, SeRPE-A*. A* surpasses greedy search and DFFS when the state space is not too large, as A* guarantees to return the optimal solution. SeRPE-A* uses a heuristic based on scores of objects shown in the table, and it will estimate the cost by total scores of objects hit by the bird.
  58. We conducted a set of experiments on a workstation in the GVIL using a Nvidia Quadro K6000
  59. and an Intel Xeon Processor, 32GB RAM
  60. Using the Chrome version of Angry Birds
  61. Under 10 minutes for time limit
  62. We use the first 9 levels of Angry Birds to evaluate different algorithms
  63. We get the statistics of the highest score for each level
  64. As well as average time cost to pass each level
  65. The results are shown in these two figures. The SeRPE-A* algorithm outperforms the naive system without using SeRPE.
  66. First
  67. Second
  68. Third
  69. Third
  70. Finally we would like to thank Prof. Nau and Vikas for teaching AI planning and advising the team. Thank you all for listening.
  71. After each shot, the entire game environment is subject to tremendous change.