Bayesian Policy Search with Policy Priors.
David WingateNoah D. GoodmanDaniel M. RoyLeslie Pack KaelblingJoshua B. TenenbaumPublished in: IJCAI (2011)
Keyphrases
- policy search
- reinforcement learning
- continuous state
- reinforcement learning algorithms
- policy gradient
- dynamic programming
- reward function
- markov decision problems
- monte carlo methods
- markov decision processes
- neural network
- robot navigation
- partially observable markov decision processes
- bayesian networks
- bayesian framework
- dynamical systems
- maximum likelihood
- state space