Bayesian Reinforcement Learning in Factored POMDPs.
Sammie KattFrans A. OliehoekChristopher AmatoPublished in: AAMAS (2019)
Keyphrases
- bayesian reinforcement learning
- partially observable markov decision processes
- state space
- optimal policy
- reinforcement learning
- finite state
- belief state
- monte carlo tree search
- dynamical systems
- dynamic programming
- decision problems
- planning under uncertainty
- markov decision processes
- partially observable
- planning problems
- heuristic search
- markov decision problems
- dynamic bayesian networks
- search space
- monte carlo
- particle filter
- evaluation function
- infinite horizon
- state variables
- multi agent
- long run
- markov chain