Central-limit approach to risk-aware Markov decision processes.
Pengqian YuJia Yuan YuHuan XuPublished in: CoRR (2015)
Keyphrases
- markov decision processes
- risk sensitive
- finite state
- state space
- reinforcement learning
- optimal policy
- decision theoretic planning
- policy iteration
- finite horizon
- dynamic programming
- planning under uncertainty
- infinite horizon
- action sets
- average cost
- reinforcement learning algorithms
- decision processes
- reward function
- factored mdps
- transition matrices
- model based reinforcement learning
- average reward
- markov decision process
- partially observable
- state and action spaces
- semi markov decision processes
- stationary policies
- reachability analysis
- decision making
- data mining