Bayesian Reinforcement Learning in Factored POMDPs.
Sammie KattFrans A. OliehoekChristopher AmatoPublished in: CoRR (2018)
Keyphrases
- bayesian reinforcement learning
- partially observable markov decision processes
- state space
- optimal policy
- reinforcement learning
- belief state
- finite state
- markov decision processes
- planning under uncertainty
- monte carlo tree search
- decision problems
- dynamical systems
- dynamic programming
- markov decision problems
- dynamic bayesian networks
- planning problems
- multi agent
- partially observable
- heuristic search
- markov chain
- approximate solutions
- learning algorithm
- initial state
- infinite horizon
- state variables
- model checking
- machine learning
- convergence rate
- decision processes
- branch and bound
- domain independent