Functional Stability of Discounted Markov Decision Processes Using Economic MPC Dissipativity Theory.
Arash Bahari KordabadSebastien GrosPublished in: CoRR (2022)
Keyphrases
- markov decision processes
- optimal policy
- policy iteration
- reinforcement learning
- finite state
- state space
- average reward
- dynamic programming
- transition matrices
- markov decision process
- factored mdps
- finite horizon
- average cost
- infinite horizon
- partially observable
- reachability analysis
- action space
- risk sensitive
- action sets
- decision processes
- planning under uncertainty
- reinforcement learning algorithms
- decision theoretic planning
- total reward
- sufficient conditions
- search algorithm
- multi agent
- decision problems
- data mining
- discount factor
- semi markov decision processes
- model based reinforcement learning
- learning algorithm