Conference on Learning Theory · 2012 · 21 citations · 10 references
ComputingAutonomous SystemsComputer ScienceArtificial IntelligenceMarkov Decision ProcessesRoboticsAutonomous ExplorationAutonomous NavigationExploration-exploitation TradeoffIntelligent AgentsReinforcement LearningReinforcement Learning FoundationsAgent LearningExplorationExtrinsic RewardsLearning AgentsMarkov Decision ModelsReinforcement Learning For NavigationReinforcement Learning ModelsReinforcement Learning Theory
While intrinsically motivated learning agents hold considerable promise to overcome limitations of more supervised learning systems, quantitative evaluation and theoretical analysis of such agents are difficult. We propose to consider a restricted setting for autonomous learning where systematic evaluation of learning performance is possible. In this setting the agent needs to learn to navigate in a Markov Decision Process where extrinsic rewards are not present or are ignored. We present a learning algorithm for this scenario and evaluate it by the amount of exploration it uses to learn the environment.
10
Near-optimal Regret Bounds for Reinforcement Learning
Thomas Jaksch, Ronald Ortner, Peter Auer · 2010 · 711 citations
Applied Physics Letters · 2000 · 528 citations · Full text