Sciweavers

40 search results - page 3 / 8
» Learning Partially Observable Action Schemas
Sort
View
COLT
2003
Springer
13 years 10 months ago
On-Line Learning with Imperfect Monitoring
We study on-line play of repeated matrix games in which the observations of past actions of the other player and the obtained reward are partial and stochastic. We define the Part...
Shie Mannor, Nahum Shimkin
AI
2007
Springer
13 years 5 months ago
Learning action models from plan examples using weighted MAX-SAT
AI planning requires the definition of action models using a formal action and plan description language, such as the standard Planning Domain Definition Language (PDDL), as inp...
Qiang Yang, Kangheng Wu, Yunfei Jiang
ICML
2008
IEEE
14 years 6 months ago
Reinforcement learning with limited reinforcement: using Bayes risk for active learning in POMDPs
Partially Observable Markov Decision Processes (POMDPs) have succeeded in planning domains that require balancing actions that increase an agent's knowledge and actions that ...
Finale Doshi, Joelle Pineau, Nicholas Roy
AIPS
2004
13 years 6 months ago
Statistical Goal Parameter Recognition
We present components of a system which uses statistical, corpus-based machine learning techniques to perform instantiated goal recognition -- recognition of both a goal schema an...
Nate Blaylock, James F. Allen
ECML
2007
Springer
13 years 11 months ago
Policy Gradient Critics
We present Policy Gradient Actor-Critic (PGAC), a new model-free Reinforcement Learning (RL) method for creating limited-memory stochastic policies for Partially Observable Markov ...
Daan Wierstra, Jürgen Schmidhuber