Bayesian RL in Factored POMDPs.
Sammie KattFrans A. OliehoekChris AmatoPublished in: BNAIC/BENELEARN (2019)
Keyphrases
- reinforcement learning
- state space
- markov decision processes
- partially observable markov decision processes
- optimal policy
- continuous state
- function approximation
- bayesian reinforcement learning
- belief state
- bayesian networks
- partially observable
- policy gradient
- dynamic programming
- action space
- learning algorithm
- policy search
- markov decision process
- machine learning
- maximum likelihood
- markov chain
- reinforcement learning methods
- dynamical systems
- multi agent
- finite state
- posterior probability
- heuristic search
- posterior distribution
- optimal control
- reinforcement learning algorithms
- planning under uncertainty
- belief space
- partial observability
- probability distribution
- search space
- transfer learning
- point based value iteration
- infinite horizon