ICML 2010 ワークショップ「強化学習と大規模探索」

概要 †

• ICML 2010 ワークショップ「強化学習と大規模探索（Reinforcement Learning and Search in Large Search Space）」
• 2010年6月25日
• イスラエル
• http://institute.unileoben.ac.at/infotech/research/workshops/icml2010-RLsearch/

プログラム †

• Optimizing Search Engines as a Dueling Bandits Problem
  Thorsten Joachims (invited talk)
• Multinomial Relevance Feedback for Content-based Image Retrieval
  Dorota Glowacka, John Shawe-Taylor
• Open Loop Optimistic Planning
  Sebastien Bubeck, Remi Munos
• Rollout Allocation Strategies for Classification-based Policy Iteration
  Victor Gabillon, Alessandro Lazaric, Mohammad Ghavamzadeh
• Sample-based Planning for Continuous Action Markov Decision Processes
  Ari Weinstein, Chris Mansley, Michael Littman
• Learning Methods for Sequential Decision Making in Practice
  Shivaram Kalyanakrishnan
• RKHS Temporal Difference Learning
  Matthew W. Robards, Peter Sunehag, Scott Sanner
• Context model inference for large or partially observable MDPs
  Christos Dimitrakakis
• Pinview: Implicit Feedback in Content-Based Image Retrieval
  Peter Auer, Zakria Hussain, Samuel Kaski, Arto Klami, Jussi Kujala, Jorma Laaksonen, Alex P. Leung, Kitsuchart Pasupa, John Shawe-Taylor