Factorized Asymptotic Bayesian Policy Search for POMDPs.
Masaaki ImaizumiRyohei FujimakiPublished in: IJCAI (2017)
Keyphrases
- policy search
- reinforcement learning
- continuous state
- partially observable markov decision processes
- continuous action
- reinforcement learning algorithms
- dynamic programming
- policy gradient
- monte carlo methods
- bayesian networks
- reward function
- markov decision problems
- dynamical systems
- decision problems
- matrix factorization
- finite state
- control policies
- multi agent
- markov decision processes
- heuristic search