機械学習研究ジャーナル JMLR

Journal of Machine Learning Researchに掲載された強化学習に関する論文．
（順次追加しており，完全なリストではありません．）

逆強化学習 †

• Inverse Reinforcement Learning in Partially Observable Environments
  Jaedeug Choi, Kee-Eung Kim
  JMLR 12:691−730 (2011)
  Keywords: inversereinforcementlearning,partiallyobservableMarkovdecisionprocess,inverse optimization, linear programming, quadratically constrained programming

POMDP †

• A Bayesian Approach for Learning and Planning in Partially Observable Markov Decision Processes
  Stéphane Ross, Joelle Pineau, Brahim Chaib-draa, Pierre Kreitmann
  JMLR 12:1729−1770 (2011)
  Keywords: reinforcement learning, Bayesian inference, partially observable Markov decision processes
• Multi-task Reinforcement Learning in Partially Observable Stochastic Environments
  Hui Li, Xuejun Liao, Lawrence Carin (Duke University)
  JMLR 10:1131-1186 (2009).
  Keywords: reinforcement learning, partially observable Markov decision processes, multi-task learning, Dirichlet processes, regionalized policy representation

転移学習 †

• Transfer Learning for Reinforcement Learning Domains: A Survey
  Matthew E. Taylor (The University of Southern California), Peter Stone (The University of Texas at Austin)
  JMLR 10:1633-1685 (2009).
  Keywords: transfer learning,reinforcement learning, multi-task learning
• Transfer Learning via Inter-Task Mappings for Temporal Difference Learning
  Matthew E. Taylor, Peter Stone, Yaxin Liu
  JMLR 8:2125-2167 (2007).
  Keywords: transfer learning, reinforcement learning, temporal difference methods, value function approximation, inter-task mapping

環境変化・動的環境 †

• Value Function Based Reinforcement Learning in Changing Markovian Environments
  Balázs Csanád Csáji, László Monostori
  JMLR 9:1679-1709 (2008).
  Keywords: Markov decision processes, reinforcement learning, changing environments, (ε,δ)- MDPs, value function bounds, stochastic iterative algorithms
• ε-MDPs: Learning in Varying Environments
  István Szita, Bálint Takács, András Lörincz
  JMLR 3:145-174 (2002).
  Keywords: reinforcement learning, convergence, event-learning, SARSA, MDP, general- ized MDP, ε-MDP, SDS controller

マルチエージェント †

• Multi-Agent Reinforcement Learning in Common Interest and Fixed Sum Stochastic Games: An Experimental Study
  Avraham Bab, Ronen I. Brafman
  JMLR 9:2635-2675 (2008).
  Keywords: reinforcement learning, multi-agent reinforcement learning, stochastic games
• Collaborative Multiagent Reinforcement Learning by Payoff Propagation
  Jelle R. Kok, Nikos Vlassis
  JMLR 7:1789-1828 (2006).
  Keywords: collaborative multiagent system, coordination graph, reinforcement learning, Q-learning, belief propagation

階層型強化学習 †

• Hierarchical Average Reward Reinforcement Learning
  Mohammad Ghavamzadeh, Sridhar Mahadevan
  JMLR 8:2629-2669 (2007).
  Keywords: semi-Markov decision processes, hierarchical reinforcement learning, average reward reinforcement learning, hierarchical and recursive optimality

バッチ学習 †

• Tree-Based Batch Mode Reinforcement Learning
  Damien Ernst, Pierre Geurts, Louis Wehenkel
  JMLR 6:503-556 (2005).
  Keywords: batch mode reinforcement learning, regression trees, ensemble methods, supervised learning, fitted value iteration, optimal control

多目的強化学習 †

• A Geometric Approach to Multi-Criterion Reinforcement Learning
  Shie Mannor, Nahum Shimkin
  JMLR 5:325-360 (2004).

探査と知識利用のジレンマ †

• Using Confidence Bounds for Exploitation-Exploration Trade-offs
  Peter Auer
  JMLR 3:397-422 (2002).
  Keywords: Online Learning, Exploitation-Exploration, Bandit Problem, Reinforcement Learning, Linear Value Function

学習分析 †

• Reinforcement Learning in Finite MDPs: PAC Analysis
  Alexander L. Strehl, Lihong Li, Michael L. Littman
  JMLR 10:2413−2444 (2009).
• Provably Efficient Learning with Typed Parametric Models
  Emma Brunskill, Bethany R. Leffler, Lihong Li, Michael L. Littman, Nicholas Roy
  JMLR 10:1955-1988 (2009).
  Keywords: reinforcement learning, provably efficient learning
• Action Elimination and Stopping Conditions for the Multi-Armed Bandit and Reinforcement Learning Problems
  Eyal Even-Dar, Shie Mannor, Yishay Mansour
  JMLR 7:1079-1105 (2006).
• Lyapunov Design for Safe Reinforcement Learning
  Theodore J. Perkins, Andrew G. Barto
  JMLR 3:803-832 (2002) .
  Keywords: Reinforcement Learning, Lyapunov Functions, Safety, Stability

TD学習 †

• Evolutionary Function Approximation for Reinforcement Learning
  Shimon Whiteson, Peter Stone
  JMLR 7:877-917 (2006).
  Keywords: reinforcement learning, temporal difference methods, evolutionary computation, neuroevolution, on-line learning
• Reinforcement Learning with Factored States and Actions
  Brian Sallans, Geoffrey E. Hinton
  JMLR 5:1063-1088 (2004).
  Keywords: product of experts, Boltzmann machine, reinforcement learning, factored actions
• Least-Squares Policy Iteration
  Michail G. Lagoudakis, Ronald Parr
  JMLR 4:1107-1149 (2003).
  Keywords: Reinforcement Learning, Markov Decision Processes, Approximate Policy Iteration, Value-Function Approximation, Least-Squares Methods

アクター・クリティック †

• A Convergent Online Single Time Scale Actor Critic Algorithm
  Dotan Di Castro, Ron Meir
  JMLR 11:367−410 (2010).
• Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning
  Evan Greensmith, Peter L. Bartlett, Jonathan Baxter
  JMLR 5:1471-1530 (2004).
  Keywords: reinforcementlearning,policygradient,baseline,actor-critic,GPOMDP

モデル・ベースド †

• R-MAX - A General Polynomial Time Algorithm for Near-Optimal Reinforcement Learning
  Ronen I. Brafman, Moshe Tennenholtz
  JMLR 3:213-231 (2002).
  Keywords: Reinforcement Learning, Learning in Games, Stochastic Games, Markov Decision Processes, Provably Efficient Learning

探査 †

• Policy Gradient in Continuous Time
  Rémi Munos
  JMLR 7:771-791 (2006).
  Keywords: optimal control, reinforcement learning, policy search, sensitivity analysis, para- metric optimization, gradient estimate, likelihood ratio method, pathwise derivation
• Policy Search using Paired Comparisons
  Malcolm J. A. Strens, Andrew W. Moore
  JMLR 3:921-950 (2002).
  Keywords: Reinforcement Learning, Policy Search, Experiment Design

ツール †

• RL-Glue: Language-Independent Software for Reinforcement-Learning Experiments
  Brian Tanner, Adam White (University of Alberta)
  JMLR 10:2133-2136 (2009).
  Keywords: reinforcement learning, empirical evaluation, standardization, open source