Clustering Markov Decision Processes For Continual Transfer.
M. M. Hassan MahmudMajd HawaslyBenjamin RosmanSubramanian RamamoorthyPublished in: CoRR (2013)
Keyphrases
- markov decision processes
- optimal policy
- finite state
- reinforcement learning
- policy iteration
- transition matrices
- planning under uncertainty
- state space
- decision theoretic planning
- infinite horizon
- dynamic programming
- finite horizon
- markov decision process
- risk sensitive
- average cost
- decision processes
- factored mdps
- action sets
- reachability analysis
- model based reinforcement learning
- average reward
- reinforcement learning algorithms
- partially observable
- state and action spaces
- action space
- semi markov decision processes
- policy evaluation
- reward function
- multistage