Approximate Value Iteration for Risk-aware Markov Decision Processes.
Pengqian YuWilliam B. HaskellHuan XuPublished in: CoRR (2017)
Keyphrases
- markov decision processes
- approximate value iteration
- policy iteration
- risk sensitive
- temporal difference learning
- fixed point
- optimal policy
- reinforcement learning
- reinforcement learning algorithms
- finite state
- decision theoretic planning
- markov decision process
- transition matrices
- markov decision problems
- state space
- dynamic programming
- planning under uncertainty
- infinite horizon
- average cost
- model free
- temporal difference
- partially observable
- decision processes
- decision making
- least squares
- reward function
- objective function
- stereo matching
- monte carlo