Monitored Markov Decision Processes.
Simone ParisiMontaser MohammedalamenAlireza KazemipourMatthew E. TaylorMichael BowlingPublished in: CoRR (2024)
Keyphrases
- markov decision processes
- finite state
- policy iteration
- state space
- optimal policy
- reinforcement learning algorithms
- dynamic programming
- reinforcement learning
- average cost
- finite horizon
- infinite horizon
- factored mdps
- transition matrices
- decision theoretic planning
- reachability analysis
- partially observable
- decision processes
- planning under uncertainty
- reward function
- action space
- model based reinforcement learning
- state and action spaces
- fixed point