CPL - Chalmers Publication Library
| Utbildning | Forskning | Styrkeområden | Om Chalmers | In English In English Ej inloggad.

ABC Reinforcement Learning

Christos Dimitrakakis (Institutionen för data- och informationsteknik, Datavetenskap, Algoritmer (Chalmers)) ; Nikolaos Tziortziotis
JMLR W&CP (ICML 2013) Vol. 28 (2013), 3, p. 684–692.
[Konferensbidrag, refereegranskat]

We introduce a simple, general framework for likelihood-free Bayesian reinforcement learning, through Approximate Bayesian Computation (ABC). The advantage is that we only require a prior distribution on a class of simulators. This is useful when a probabilistic model of the underlying process is too complex to formulate, but where detailed simulation models are available. ABC-RL allows the use of any Bayesian reinforcement learning technique in this case. It can be seen as an extension of simulation methods to both planning and inference. We experimentally demonstrate the potential of this approach in a comparison with LSPI. Finally, we introduce a theorem showing that ABC is sound.

Nyckelord: reinforcement learning; approximate Bayesian computation



Den här publikationen ingår i följande styrkeområden:

Läs mer om Chalmers styrkeområden  

Denna post skapades 2013-09-17. Senast ändrad 2015-01-08.
CPL Pubid: 183500