PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Reinforcement Learning with Limited Reinforcement: Using Bayes-Risk for Active Learning in POMDPS
Finale Doshi, Joelle Pineau and Nicholas Roy
In: ICML 2008, Helsinki, Finland(2008).


Partially Observable Markov Decision Processes (POMDPs) have succeeded in planning domains that require balancing actions that increase an agent's knowledge and actions that increase an agent's reward. Unfortunately, most POMDPs are defined with a large number of parameters which are difficult to specify only from domain knowledge. In this paper, we present an approximation approach that allows us to treat the POMDP model parameters as additional hidden state in a ``model-uncertainty'' POMDP. Coupled with model-directed queries, our planner actively learns good policies. We demonstrate our approach on several POMDP problems.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:4378
Deposited By:Finale Doshi
Deposited On:13 March 2009