A Convex Analytic Approach to Risk-Aware Markov Decision Processes.
William B. HaskellRahul JainPublished in: SIAM J. Control. Optim. (2015)
Keyphrases
- markov decision processes
- risk sensitive
- finite state
- state space
- optimal policy
- transition matrices
- decision theoretic planning
- reinforcement learning
- policy iteration
- planning under uncertainty
- reachability analysis
- factored mdps
- average reward
- reinforcement learning algorithms
- average cost
- partially observable
- semi markov decision processes
- infinite horizon
- state and action spaces
- decision processes
- model based reinforcement learning
- finite horizon
- action space
- markov decision process
- dynamic programming
- state abstraction
- data mining
- action sets
- optimal control
- learning algorithm