Constrained Markov decision processes with uncertain costs.
V. VaragapriyaVikas Vikram SinghAbdel LisserPublished in: Oper. Res. Lett. (2022)
Keyphrases
- markov decision processes
- average cost
- optimal policy
- finite state
- reinforcement learning
- transition matrices
- state space
- dynamic programming
- decision theoretic planning
- policy iteration
- planning under uncertainty
- decision making
- average reward
- partially observable
- decision processes
- reinforcement learning algorithms
- infinite horizon
- finite horizon
- reachability analysis
- risk sensitive
- action sets
- total cost
- action space
- long run
- factored mdps
- model based reinforcement learning
- markov decision process