Learning and Planning in Markov Processes — Advances and Challenges
Papers from the 2004 AAAI Workshop
Daniela Pucci de Farias, Shie Mannor, Doina Precup, and Georgios Theocharous, Program Cochairs
Technical Report WS-04-08 published by The AAAI Press, Menlo Park, California
This technical report is also available in book and CD format.
Please Note: Abstracts are linked to individual titles, and will appear in a separate browser window. Full-text versions of the papers are linked to the abstract text. Access to full text may be restricted to AAAI members. PDF file sizes may be large!
Contents
Organizing Committee / iii
Daniela Pucci de Farias, Shie Mannor, Doina Precup, and Georgios Theocharous
Planning in Belief Space with a Labelled Uncertainty Graph / 1
Daniel Bryce, Subbarao Kambhampati, and David E. Smith
An Approach to State Aggregation for POMDPs / 7
Zhengzhu Feng and Eric A. Hansen
Manifold Representations for Value-Function Approximations / 13
Robert Glaubius and William D. Smart
Solving Factored MDPs with Continuous and Discrete Variables / 19
Carlos Guestrin, Milos Hauskrecht, and Branislav Kveton
Dynamic Programming for Partially Observable Stochastic Games / 25
Eric A. Hansen, Daniel S. Bernstein, and Shlomo Zilberstein
A Logic-based Approach to Dynamic Programming / 31
Steffen Hölldobler and Olga Skvortsova
Towards Learning to Ignore Irrelevant State Variables / 37
Nicholas K. Jong and Peter Stone
Focus of Attention in Sequential Decision Making / 43
Lihong Li, Vadim Bulitko, and Russell Greiner
Existence and Finiteness Conditions for Risk-Sensitive Planning: First Results / 49
Yaxin Liu and Sven Koenig
Concurrent Hierarchical Reinforcement Learning / 55
Bhaskara Marthi, David Latham, Stuart Russell, and Carlos Guestrin
Concurrent Probabilistic Temporal Planning: Initial Results / 60
Mausam and Daniel S. Weld
Scaling Up Decision Theoretic Planning to Planetary Rover Problems / 66
Nicolas Meuleau, Richard Dearden, and Rich Washington
Robust Solutions to Markov Decision Problems / 72
Arnab Nilim and Laurent El Ghaoui
Self-Organizing Perceptual and Temporal Abstraction for Robot Reinforcement Learning / 79
Jefferson Provost, Benjamin J. Kuipers, and Risto Miikkulainen
Sparse Distributed Memories in Reinforcement Learning: Case Studies / 85
Bohdana Ratitch, Swaminathan Mahadevan, and Doina Precup
Local Graph Partitioning as a Basis for Generating Temporally-Extended Actions in Reinforcement Learning / 91
Özgür Simsek, Alicia P. Wolfe, and Andrew G. Barto
Studying Human Spatial Navigation Processes Using POMDPs / 97
Brian J. Stankiewicz, Matthew McCabe, and Gordon E. Legge
Cache Performance of Priority Metrics for MDP Solver / 103
David Wingate and Kevin D. Seppi
A Formalism for Stochastic Decision Processes with Asynchronous Events / 107
Håkan L. S. Younes and Reid G. Simmons