Reinforcement Learning

Action-Gap Phenomenon in Reinforcement Learning NeurIPS 2011 Agnostic KWIK learning and efficient approximate reinforcement learning COLT 2011 Analysis and Improvement of Policy Gradient Estimation NeurIPS 2011 A Non-Parametric Approach to Dynamic Programming NeurIPS 2011 A Reinforcement Learning Theory for Homeostatic Regulation NeurIPS 2011 A reinterpretation of the policy oscillation phenomenon in approximate policy iteration NeurIPS 2011 Blending Autonomous Exploration and Apprenticeship Learning NeurIPS 2011 Committing Bandits NeurIPS 2011 Contextual Bandits with Linear Payoff Functions AISTATS 2011 Convergent Fitted Value Iteration with Linear Function Approximation NeurIPS 2011 Dynamic Policy Programming with Function Approximation AISTATS 2011 Environmental statistics and the trade-off between model-based and TD learning in humans NeurIPS 2011 Evaluating the inverse decision-making approach to preference learning NeurIPS 2011 Global Motion Planning under Uncertain Motion, Sensing, and Environment Map RSS 2011 Learning to Agglomerate Superpixel Hierarchies NeurIPS 2011 MAP Inference for Bayesian Inverse Reinforcement Learning NeurIPS 2011 Minimax Regret of Finite Partial-Monitoring Games in Stochastic Environments COLT 2011 Monotone multi-armed bandit allocations COLT 2011 Nonlinear Inverse Reinforcement Learning with Gaussian Processes NeurIPS 2011 Optimal Reinforcement Learning for Gaussian Systems NeurIPS 2011 Periodic Finite State Controllers for Efficient POMDP and DEC-POMDP Planning NeurIPS 2011 Reinforcement Learning using Kernel-Based Stochastic Factorization NeurIPS 2011 Selecting the State-Representation in Reinforcement Learning NeurIPS 2011 Speedy Q-Learning NeurIPS 2011 TD_gamma: Re-evaluating Complex Backups in Temporal Difference Learning NeurIPS 2011