University of Alberta Library · 2010 · 39 citations · 27 references
ComputingAutonomous SystemsComputer ScienceArtificial IntelligenceDistributed SystemsMachine LearningAgent-based SimulationGame PlayingGame-based LearningIntelligent AgentsMulti-agent SystemsReinforcement LearningArtificial AgentsArtificial Intelligence In GamesGame EnginesGame-playing AgentsGame-theoretic Agent DesignIndependent Agents
This research focuses on developing AI agents that play arbitrary Atari 2600 console games without having any game-specific assumptions or prior knowledge. Two main approaches are considered: reinforcement learning based methods and search based methods. The RL-based methods use feature vectors generated from the game screen as well as the console RAM to learn to play a given game. The search-based methods use the emulator to simulate the consequence of actions into the future, aiming to play as well as possible by only exploring a very small fraction of the state-space. To insure the generic nature of our methods, all agents are designed and tuned using four specific games. Once the development and parameter selection is complete, the performance of the agents is evaluated on a set of 50 randomly selected games. Significant learning is reported for the RL-based methods on most games. Additionally, some instances of human-level performance is achieved by the search-based methods.
27
Increased rates of convergence through learning rate adaptation
Robert A. Jacobs · Neural Networks · 1988 · 1.8K citations
Murray Campbell, A. Joseph Hoane, Feng-hsiung Hsu · Artificial Intelligence · 2002 · 1.2K citations
Richard E. Korf · Artificial Intelligence · 1990 · 919 citations
General Game Playing: Overview of the AAAI Competition
Michael Genesereth, Nathaniel Love, Barney Pell · 2005 · 543 citations