Online Learning in Markov Decision Processes with Continuous Actions.
Yi-Te HongChi-Jen LuPublished in: ALT (2015)
Keyphrases
- markov decision processes
- online learning
- action space
- state and action spaces
- decision theoretic planning
- action sets
- partially observable
- state space
- continuous state
- finite state
- optimal policy
- decision processes
- reinforcement learning
- reward function
- dynamic programming
- continuous state spaces
- policy iteration
- e learning
- average cost
- macro actions
- transition matrices
- markov decision process
- planning under uncertainty
- finite horizon
- reachability analysis
- reinforcement learning algorithms
- stochastic games
- active learning
- markov decision problems
- average reward
- semi markov decision processes
- model based reinforcement learning
- factored mdps
- infinite horizon
- data mining