Incremental Least Squares Policy Iteration for POMDPs.
Hui LiXuejun LiaoLawrence CarinPublished in: AAAI (2006)
Keyphrases
- reinforcement learning
- policy iteration
- belief state
- incremental learning
- markov decision processes
- reinforcement learning methods
- model free
- partially observable markov decision processes
- continuous state
- dynamic programming
- continuous state spaces
- dynamical systems
- policy gradient
- temporal difference
- state action
- neural network
- distributed constraint optimization
- reinforcement learning algorithms
- partially observable
- finite state
- state space
- optimal solution
- bayesian networks
- policy search
- machine learning