Multiple-Environment Markov Decision Processes.
Jean-François RaskinOcan SankurPublished in: CoRR (2014)
Keyphrases
- markov decision processes
- state space
- optimal policy
- decision processes
- finite state
- policy iteration
- reinforcement learning
- reachability analysis
- transition matrices
- infinite horizon
- average cost
- average reward
- decision theoretic planning
- partially observable
- markov decision process
- model based reinforcement learning
- semi markov decision processes
- finite horizon
- action space
- factored mdps
- action sets
- dynamic programming
- dynamic environments
- learning algorithm
- state and action spaces
- mobile robot
- reinforcement learning algorithms