Randomized and Relaxed Strategies in Continuous-Time Markov Decision Processes.
Alexey B. PiunovskiyPublished in: SIAM J. Control. Optim. (2015)
Keyphrases
- markov decision processes
- state space
- optimal policy
- finite state
- transition matrices
- reinforcement learning
- stationary policies
- markov chain
- policy iteration
- reachability analysis
- decision theoretic planning
- finite horizon
- reinforcement learning algorithms
- average reward
- planning under uncertainty
- dynamic programming
- model based reinforcement learning
- average cost
- action space
- partially observable
- decision processes
- markov decision process
- risk sensitive
- factored mdps
- infinite horizon
- optimal control
- semi markov decision processes
- real time dynamic programming
- state and action spaces
- reward function
- heuristic search
- optimal solution
- objective function