Reinforcement Learning in Real-Time Strategy Games Nick Imrei Supervisors: Matthew Mitchell & Martin Dick.

Slides:



Advertisements
Similar presentations
Modelling CGFs for tactical air-to-air combat training
Advertisements

1 Chapter 8 Looking Smart maximizing perception of intelligence Reference: Game Development Essentials Game Artificial Intelligence.
A Survey of Real-Time Strategy Game AI Research and Competition in StarCraft Santiago Ontanon, Gabriel Synnaeve, Alberto Uriarte, Florian Richoux, David.
Artificial Intelligence in Real Time Strategy Games Dan Li.
Machine Learning in Computer Games Learning in Computer Games By: Marc Ponsen.
The AGILO Autonomous Robot Soccer Team: Computational Principles, Experiences, and Perspectives Michael Beetz, Sebastian Buck, Robert Hanek, Thorsten Schmitt,
Class Project Due at end of finals week Essentially anything you want, so long as it’s AI related and I approve Any programming language you want In pairs.
Will Androids Dream of Electric Sheep? A Glimpse of Current and Future Developments in Artificial Intelligence Henry Kautz Computer Science & Engineering.
Learning Shape in Computer Go David Silver. A brief introduction to Go Black and white take turns to place down stones Once played, a stone cannot move.
Evolving Neural Network Agents in the NERO Video Game Author : Kenneth O. Stanley, Bobby D. Bryant, and Risto Miikkulainen Presented by Yi Cheng Lin.
Reinforcement Learning of Local Shape in the Game of Atari-Go David Silver.
XYZ 6/18/2015 MIT Brain and Cognitive Sciences Convergence Analysis of Reinforcement Learning Agents Srinivas Turaga th March, 2004.
CIC Launch Event Artificial Intelligence in Computer Games Dr Tim Gosling The Creative Assembly.
Reinforcement Learning in Real- Time Strategy Games Nick Imrei Supervisors: Matthew Mitchell & Martin Dick.
Reinforcement Learning Game playing: So far, we have told the agent the value of a given board position. How can agent learn which positions are important?
Reinforcement Learning of Local Shape in the Game of Atari-Go David Silver.
RoboCup: The Robot World Cup Initiative Based on Wikipedia and presentations by Mariya Miteva, Kevin Lam, Paul Marlow.
Neural Networks Slides by Megan Vasta. Neural Networks Biological approach to AI Developed in 1943 Comprised of one or more layers of neurons Several.
CS Machine Learning. What is Machine Learning? Adapt to / learn from data  To optimize a performance function Can be used to:  Extract knowledge.
AI and GAMES CSC 8520, Villanova University Spring, 2004 Paula Matuszek & Robin McEntire.
10.3 Understanding Pattern Recognition Methods Chris Kramer.
SOFTWARE ADAPTIVITY THROUGH XML-BASED BUSINESS RULES AND AGENTS Queen’s University of Belfast, School of Computer Science, Belfast, United Kingdom Liang.
Artificial Intelligence in Game Design Problems and Goals.
Introduction (Chapter 1) CPSC 386 Artificial Intelligence Ellen Walker Hiram College.
Current Situation and Future Plans Abdelrahman Al-Ogail & Omar Enayet October
Enemy Agent Responding to stimuli in a real time 3D environment.
More precisely called Branch of AI behind it.
Introduction Many decision making problems in real life
Computer Go : A Go player Rohit Gurjar CS365 Project Proposal, IIT Kanpur Guided By – Prof. Amitabha Mukerjee.
Introduction to AI Engine & Common Used AI Techniques Created by: Abdelrahman Al-Ogail Under Supervision of: Dr. Ibrahim Fathy.
TEMPLATE DESIGN © Last Resort Animation, Modeling, AI, Networking, and Backend Alex Bunch, Nick Hunter, Austin Lohr, Robert.
Integrating Background Knowledge and Reinforcement Learning for Action Selection John E. Laird Nate Derbinsky Miller Tinkerhess.
AI and Computer Games (informational session) Lecture by: Dustin Dannenhauer Professor Héctor Muñoz-Avila Computer Science and Eng.
CSC Intro. to Computing Lecture 22: Artificial Intelligence.
Chap. 1 GENERAL WISDOM AI Game Programming Wisdom.
1 CS 4701 – Project Proposal Jane Park (jp624) Ran Zhao (rz54)
Ibrahim Fathy, Mostafa Aref, Omar Enayet, and Abdelrahman Al-Ogail Faculty of Computer and Information Sciences Ain-Shams University ; Cairo ; Egypt.
Artificial Life/Agents Creatures: Artificial Life Autonomous Software Agents for Home Entertainment Stephen Grand, 1997 Learning Human-like Opponent Behaviour.
CHECKERS: TD(Λ) LEARNING APPLIED FOR DETERMINISTIC GAME Presented By: Presented To: Amna Khan Mis Saleha Raza.
Game Theory, Social Interactions and Artificial Intelligence Supervisor: Philip Sterne Supervisee: John Richter.
Curiosity-Driven Exploration with Planning Trajectories Tyler Streeter PhD Student, Human Computer Interaction Iowa State University
CSCI 4310 Lecture 6: Adversarial Tree Search. Book Winston Chapter 6.
Top level learning Pass selection using TPOT-RL. DT receiver choice function DT is trained off-line in artificial situation DT used in a heuristic, hand-coded.
Artificial intelligence
Carla P. Gomes CS4700 CS 4701: Practicum in Artificial Intelligence Carla P. Gomes
Intelligent Database Systems Lab 國立雲林科技大學 National Yunlin University of Science and Technology 1 Evolving Reactive NPCs for the Real-Time Simulation Game.
Algorithmic, Game-theoretic and Logical Foundations
Pac-Man AI using GA. Why Machine Learning in Video Games? Better player experience Agents can adapt to player Increased variety of agent behaviors Ever-changing.
Artificial Intelligence Research in Video Games By Jacob Schrum
Course Overview  What is AI?  What are the Major Challenges?  What are the Main Techniques?  Where are we failing, and why?  Step back and look at.
Artificial Intelligence in Games
1 Multiagent Teamwork: Analyzing the Optimality and Complexity of Key Theories and Models David V. Pynadath and Milind Tambe Information Sciences Institute.
28th of July 2005Learning in Strategy Games1 COMPSCI777 – Computer Games Technology Learning in Strategy Games The University Of Auckland Thursday the.
Contested Dominion Game Treatment written by Nicholas Mezza.
Reinforcement Learning AI – Week 22 Sub-symbolic AI Two: An Introduction to Reinforcement Learning Lee McCluskey, room 3/10
Artificial Intelligence: Research and Collaborative Possibilities a presentation by: Dr. Ernest L. McDuffie, Assistant Professor Department of Computer.
Artificial Intelligence, simulation and modelling.
Goo Wars Clausewitz Sandbox Shapes Mass Size Density Motivation Ancient War is the interaction of shapes. Fighting occurs at the intersection of these.
Designing Intelligence Logical and Artificial Intelligence in Games Lecture 2.
CAP6938 Neuroevolution and Artificial Embryogeny Real-time NEAT Dr. Kenneth Stanley February 22, 2006.
2013 Section Meeting Coaching Workshop Maximizing Coaching Moments with Young Players.
The Game Development Process: Artificial Intelligence.
Team Member AI in an FPS and Goal Oriented Action Planning.
Brief Intro to Machine Learning CS539
RoboCup: The Robot World Cup Initiative
A Conceptual Design of Multi-Agent based Personalized Quiz Game
Learning Fast and Slow John E. Laird
Done Done Course Overview What is AI? What are the Major Challenges?
School of Computing Science
Reinforcement Learning for Adaptive Game Learner
Presentation transcript:

Reinforcement Learning in Real-Time Strategy Games Nick Imrei Supervisors: Matthew Mitchell & Martin Dick

Outline Reasons What this research is about Motivation and Aim Background RTS games Reinforcement Learning explained Applying RL to RTS This project Methodology Evaluation Summary

Motivation and Aims Problem: AI has been a neglected area – game developers have adopted the “not broken so why fix it” philosophy Internet Thrashing – my own experience Aim: Use learning to develop a human-like player Simulate beginner → intermediate level play Use RL and A-life-like techniques E.g. Black and White, Pengi [Scott]

RTS Games – The Domain Two or more teams of individuals/cohorts in a war- like situation on a series of battlefields E.g. Command & Conquer, Starcraft, Age of Empires, Red Alert, Empire Earth Teams can have a variety of: Weapons Units Resources Buildings Players required to manage all of the above to achieve the end goal. (Destroy all units, capture flag, etc.)

Challenges offered in RTS games Real time constraints on actions High level strategies combined with low- level tactics Multiple goals and choices

The Aim and Approach Create a human-like opponent Realistic Diverse behavior (not boring) This is difficult to do! Tactics and Strategy Agents will be reactive to environment Learn rather than code – Reinforcement learning

The Approach Part 1 – Reinforcement Learning Reward and Penalty Action Rewards / Penalties Penalize being shot Reward killing a player on the other team Strategic Rewards / Penalties Securing / occupying a certain area Staying in certain group formations Destroying all enemy units Aim to receive maximum reward over time Problem: Credit assignment What rewards should be given to which behaviors?

The Approach Part 2 – Credit Assignment States and actions Decide on a state space and action space Assign values to States, or States and Actions Train the agent in this space

Reinforcement Learning example

Why use Reinforcement Learning? Well suited to problems where there is a delayed reward (tactics and strategy) The trained agent moves in (worst case) linear time (reactive) Problems: Large state spaces (state aggregation) Long training times (ER and shaping)

The Approach Part 3 – Getting Diversity Agent Agent state space A-life-like behavior using aggregated state spaces

Research Summary: Investigate this approach using a simple RTS game Issues: Empirical Research Applying RL in a novel way Not using entire state space Need to investigate Appropriate reward functions Appropriate state spaces Problems with Training Will need lots of trials - the propagation problem No. trials can be reduced using Shaping [Mahadevan] and Experience Replay [Lin] Self play – other possibilities include A* and human opponents Tesauro, Samuel

Methodology Hypothesis: “The combination of RL and reduced state spaces in a rich (RTS) environment will lead to human-like gameplay” Empirical investigation to test hypothesis Evaluate system behavior Analyze the observed results Describe interesting phenomenon

Evaluation Measure the diversity of strategies How big a change (and what type) is required to change the behaviour – a qualitative analysis of this Success of strategies I.e. what level of gameplay does it achieve Time to win, points scored, resembles humans Compare to human strategies “10 requirements of a challenging and realistic opponent” [Scott]

Summary Interested in a human-level game program Want to avoid brittle, predictable programmed solutions Search program space for most diverse solutions using RL to direct search Allows specifications of results, without needing to specify how this can be achieved Evaluate the results

References Bob Scott. The illusion of intelligence. AI Game Programming Wisdom, pages 16–20, Sridhar Mahadevan and Jonathan Connell. Automatic programming of behavior-based robots using reinforcement learning. Artificial Intelligence 55, pages 311–364, L Lin. Reinforcement learning for robots using neural networks. PhD thesis, School of Computer Science, Carnegie Mellon University, Pittsburgh USA, Mark Bishop Ring. Continual Learning in Reinforcement Environments. MIT Press, 1994.

Stay Tuned! For more information, see Thanks for listening!