Realizable Strategies in Continuous-Time Markov Decision Processes.
Alexey B. PiunovskiyPublished in: SIAM J. Control. Optim. (2018)
Keyphrases
- markov decision processes
- state space
- optimal policy
- finite state
- transition matrices
- dynamic programming
- reinforcement learning
- markov chain
- reachability analysis
- reinforcement learning algorithms
- stationary policies
- policy iteration
- markov decision process
- factored mdps
- action space
- infinite horizon
- finite horizon
- average cost
- decision processes
- average reward
- planning under uncertainty
- action sets
- model based reinforcement learning
- risk sensitive
- decision theoretic planning
- partially observable
- reward function
- optimal control
- optimal solution