Federated Control in Markov Decision Processes.
Hao JinYang PengLiangyu ZhangZhihua ZhangPublished in: CoRR (2024)
Keyphrases
- markov decision processes
- optimal policy
- reinforcement learning
- transition matrices
- finite state
- dynamic programming
- policy iteration
- state space
- finite horizon
- decentralized control
- infinite horizon
- control system
- reinforcement learning algorithms
- action sets
- control problems
- average reward
- average cost
- markov decision process
- decision theoretic planning
- optimal control
- planning under uncertainty
- decision processes
- risk sensitive
- state and action spaces
- partially observable
- control strategy
- factored mdps
- reachability analysis
- semi markov decision processes
- monte carlo
- model based reinforcement learning
- machine learning