機械学習国際会議 ICML 2010

概要 †

• 第27回機械学習国際会議（The 27th International Conference on Machine Learning）
• 2010年6月21日-24日
• イスラエル
• http://www.icml2010.org/

Reinforcement Learning 1 †

• Least-Squares Λ Policy Iteration: Bias-Variance Trade-off in Control Problems
  Christophe Thiery (Loria); Bruno Scherrer (Loria)
• Finite-Sample Analysis of LSTD
  Alessandro Lazaric (Inria); Mohammad Ghavamzadeh (Inria); Remi Munos (Inria)
• Convergence of Least Squares Temporal Difference Methods Under General Conditions
  Huizhen Yu (Univ. of Helsinki)
• Should one compute the Temporal Difference fix point or minimize the Bellman Residual? The unified oblique projection view
  Bruno Scherrer (Loria)

Reinforcement Learning 2 †

• Approximate Predictive Representations of Partially Observable Systems
  Doina Precup (Mcgill University); Monica Dinculescu (McGill University)
• Constructing States for Reinforcement Learning
  M. M. Mahmud (Australian National University)
• Temporal Difference Bayesian Model Averaging: A Bayesian Perspective on Adapting Lambda
  Carlton Downey (Victoria University of Wellington); Scott Sanner (Nicta)
• Bayesian Multi-Task Reinforcement Learning
  Alessandro Lazaric (Inria); Mohammad Ghavamzadeh (Inria)

Reinforcement Learning 3 †

• Generalizing Apprenticeship Learning across Hypothesis Classes
  Thomas Walsh (Rutgers University); Kaushik Subramanian (Rutgers University); Michael Littman (Rutgers University); Carlos Diuk (Princeton University)
• Toward Off-Policy Learning Control with Function Approximation
  Hamid Maei (University of Alberta); Csaba Szepesvari (University Of Alberta); Shalabh Bhatnagar (Indian Institute of Science); Richard Sutton (University of Alberta)
• Efficient Reinforcement Learning with Multiple Reward Functions for Randomized Controlled Trial Analysis
  Daniel Lizotte (University of Michigan); Michael Bowling (University of Alberta); Susan Murphy (University of Michigan)
• Internal Rewards Mitigate Agent Boundedness Jonathan Sorg (University of Michigan); Satinder Singh (University of Michigan); Richard Lewis (University of Michigan)

Reinforcement Learning 4 †

• Analysis of a Classification-based Policy Iteration Algorithm
  Alessandro Lazaric (Inria); Mohammad Ghavamzadeh (Inria); Remi Munos (Inria)
• Nonparametric Return Distribution Approximation for Reinforcement Learning
  Tetsuro Morimura (IBM Research - Tokyo); Masashi Sugiyama (Tokyo Institute Of Technology); Hisashi Kashima (University of Tokyo); Hirotaka Hachiya; Toshiyuki Tanaka
• Inverse Optimal Control with Linearly Solvable MDPs
  Krishnamurthy Dvijotham (University of Washington); Emanuel Todorov (University of Washington)
• Feature Selection Using Regularization in Approximate Linear Programs for Markov Decision Processes
  Marek Petrik (University of Massachusetts ); Gavin Taylor (Duke); Ron Parr (Duke); Shlomo Zilberstein (University of Massachusetts Amherst)