Reversible Markov decision processes and the Gaussian free field.
Venkat AnantharamPublished in: Syst. Control. Lett. (2022)
Keyphrases
- markov decision processes
- state space
- optimal policy
- finite state
- transition matrices
- policy iteration
- dynamic programming
- reinforcement learning algorithms
- decision theoretic planning
- markov chain
- planning under uncertainty
- reinforcement learning
- factored mdps
- average cost
- model based reinforcement learning
- markov decision process
- partially observable
- infinite horizon
- average reward
- finite horizon
- risk sensitive
- action space
- reachability analysis
- state and action spaces
- semi markov decision processes
- decision processes
- real time dynamic programming
- state abstraction