Relevance Vector Sampling for Reinforcement Learning in Continuous Action Space.
Minwoo LeeCharles W. AndersonPublished in: ICMLA (2016)
Keyphrases
- action space
- reinforcement learning
- state space
- markov decision processes
- state and action spaces
- continuous state
- real valued
- continuous state spaces
- control policies
- stochastic processes
- action selection
- function approximation
- state action
- single agent
- reinforcement learning methods
- optimal policy
- multi agent
- markov decision problems
- function approximators
- reinforcement learning algorithms
- continuous action
- information retrieval
- markov decision process
- markov chain
- cooperative
- reward function
- model free
- multiple agents
- optimal control
- sufficient conditions
- particle filter
- policy search
- learning algorithm