Markov Decision Processes with Long-Term Average Constraints.
Mridul AgarwalQinbo BaiVaneet AggarwalPublished in: CoRR (2021)
Keyphrases
- markov decision processes
- long term
- average cost
- optimal policy
- state space
- finite state
- transition matrices
- discounted reward
- planning under uncertainty
- policy iteration
- reinforcement learning
- decision theoretic planning
- finite horizon
- reachability analysis
- dynamic programming
- average reward
- partially observable
- markov decision process
- model based reinforcement learning
- factored mdps
- reward function
- risk sensitive
- policy evaluation
- reinforcement learning algorithms
- action sets
- decision processes
- infinite horizon
- sufficient conditions
- state and action spaces