Learning physically-instantiated game play through visual observation

Barbu, Andrei; Narayanaswamy, Siddharth; Siskind, Jeffrey Mark

doi:10.1109/robot.2010.5509925

Cited by 15 publications

(13 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) While the GGP competition provides a description of game dynamics, algorithms studied in this article must learn dynamics exclusively by playing the game. (3) While the GGP competition is based on declarative representations, this article focuses on visual representations (as suggested by other recent work in GGP [1,22]) (4) While GGP features board-like games, this article takes a step towards playing video games.…”

Section: Related Workmentioning

confidence: 99%

A Neuroevolution Approach to General Atari Game Playing

Hausknecht

Lehman

Miikkulainen

et al. 2014

IEEE Trans. Comput. Intell. AI Games

139

View full text Add to dashboard Cite

This article addresses the challenge of learning to play many different video games with little domainspecific knowledge. Specifically, it introduces a neuro-evolution approach to general Atari 2600 game playing. Four neuro-evolution algorithms were paired with three different state representations and evaluated on a set of 61 Atari games. The neuro-evolution agents represent different points along the spectrum of algorithmic sophistication -including weight evolution on topologically fixed neural networks (Conventional Neuro-evolution), Covariance Matrix Adaptation Evolution Strategy (CMA-ES), evolution of network topology and weights (NEAT), and indirect network encoding (HyperNEAT). State representations include an object representation of the game screen, the raw pixels of the game screen, and seeded noise (a comparative baseline). Results indicate that direct-encoding methods work best on compact state representations while indirect-encoding methods (i.e. HyperNEAT) allow scaling to higher-dimensional representations (i.e. the raw game screen). Previous approaches based on temporaldifference learning had trouble dealing with the large state spaces and sparse reward gradients often found in Atari games. Neuro-evolution ameliorates these problems and evolved policies achieve state-of-the-art results, even surpassing human high scores on three games. These results suggest that neuro-evolution is a promising approach to general video game playing.

show abstract

Section: Related Workmentioning

confidence: 99%

A Neuroevolution Approach to General Atari Game Playing

Hausknecht

Lehman

Miikkulainen

et al. 2014

IEEE Trans. Comput. Intell. AI Games

139

View full text Add to dashboard Cite

show abstract

“…This shows that for the purpose of General Game Playing the language GDL-II can be considered complete; additional elements can only serve to obtain more succinct descriptions (e.g., by allowing explicit specifications of non-uniform probabilities for moves by random) or will be needed when the very concept of General Game Playing itself is extended beyond the current setting, e.g. to open-world games such as Scrabble (Sheppard, 2002) or systems that play real, physical games (Barbu, Narayanaswamy, & Siskind, 2010).…”

Section: Resultsmentioning

confidence: 99%

Representing and Reasoning About the Rules of General Games With Imperfect Information

Schiffel

Thielscher

2014

jair

View full text Add to dashboard Cite

A general game player is a system that can play previously unknown games just by being given their rules. For this purpose, the Game Description Language (GDL) has been developed as a high-level knowledge representation formalism to communicate game rules to players. In this paper, we address a fundamental limitation of state-of-the-art methods and systems for General Game Playing, namely, their being confined to deterministic games with complete information about the game state. We develop a simple yet expressive extension of standard GDL that allows for formalising the rules of arbitrary finite, n-player games with randomness and incomplete state knowledge. In the second part of the paper, we address the intricate reasoning challenge for general game-playing systems that comes with the new description language. We develop a full embedding of extended GDL into the Situation Calculus augmented by Scherl and Levesque's knowledge fluent . We formally prove that this provides a sound and complete reasoning method for players' knowledge about game states as well as about the knowledge of the other players.

show abstract

“…A second broad area for future work is that of learning. Instead of having to describe new games in GDL, it would be beneficial if the robot were able to learn how to play a game by being shown how by a user, as in [8,1].…”

Section: Discussionmentioning

confidence: 99%

Towards General Game-Playing Robots: Models, Architecture and Game Controller

Rajaratnam

Thielscher

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. General Game Playing aims at AI systems that can understand the rules of new games and learn to play them effectively without human intervention. Our paper takes the first step towards general game-playing robots, which extend this capability to AI systems that play games in the real world. We develop a formal model for general games in physical environments and provide a systems architecture that allows the embedding of existing general game players as the "brain" and suitable robotic systems as the "body" of a general game-playing robot. We also report on an initial robot prototype that can understand the rules of arbitrary games and learns to play them in a fixed physical game environment.

show abstract

Learning physically-instantiated game play through visual observation

Cited by 15 publications

References 13 publications

A Neuroevolution Approach to General Atari Game Playing

A Neuroevolution Approach to General Atari Game Playing

Representing and Reasoning About the Rules of General Games With Imperfect Information

Towards General Game-Playing Robots: Models, Architecture and Game Controller

Contact Info

Product

Resources

About