Constrained Markov Decision Processes with Expected Total Reward Criteria.
Anna JaskiewiczAndrzej S. NowakPublished in: SIAM J. Control. Optim. (2019)
Keyphrases
- total reward
- markov decision processes
- average reward
- optimal policy
- reinforcement learning algorithms
- finite state
- reinforcement learning
- state space
- optimality criterion
- policy iteration
- stationary policies
- decision processes
- transition matrices
- decision theoretic planning
- action selection
- dynamic programming
- average cost
- action space
- infinite horizon
- partially observable markov decision processes
- markov decision process
- reward function
- long run
- planning under uncertainty
- sufficient conditions
- decision making