Approximate Value Iteration for Risk-Aware Markov Decision Processes.
Pengqian YuWilliam B. HaskellHuan XuPublished in: IEEE Trans. Autom. Control. (2018)
Keyphrases
- markov decision processes
- approximate value iteration
- policy iteration
- risk sensitive
- temporal difference learning
- fixed point
- reinforcement learning algorithms
- reinforcement learning
- markov decision process
- optimal policy
- state space
- markov decision problems
- finite state
- infinite horizon
- transition matrices
- decision theoretic planning
- partially observable
- average cost
- decision processes
- action space
- planning under uncertainty
- dynamic programming
- decision making
- optimal control
- reward function