Constrained Markov Decision Processes with Non-constant Discount Factor.
Héctor Jasso-FuentesTomás Prieto-RumeauPublished in: J. Optim. Theory Appl. (2024)
Keyphrases
- markov decision processes
- discount factor
- optimal policy
- average reward
- partially observable
- finite state
- state space
- reinforcement learning
- policy iteration
- markov decision problems
- reinforcement learning algorithms
- dynamic programming
- average cost
- decision processes
- planning under uncertainty
- infinite horizon
- finite horizon
- decision problems
- action space