Markov decision processes with burstiness constraints.
Michal GolanNahum ShimkinPublished in: Eur. J. Oper. Res. (2024)
Keyphrases
- markov decision processes
- state space
- optimal policy
- finite state
- policy iteration
- dynamic programming
- reinforcement learning
- planning under uncertainty
- transition matrices
- decision theoretic planning
- finite horizon
- action space
- partially observable
- average reward
- reinforcement learning algorithms
- markov decision process
- infinite horizon
- model based reinforcement learning
- action sets
- risk sensitive
- factored mdps
- average cost
- decision processes
- state and action spaces
- decision makers
- reachability analysis
- state abstraction
- monte carlo