Discounted Continuous-Time Markov Decision Processes with Constraints: Unbounded Transition and Loss Rates.
Xianping GuoAlexei B. PiunovskiyPublished in: Math. Oper. Res. (2011)
Keyphrases
- markov decision processes
- state space
- optimal policy
- reinforcement learning
- finite state
- dynamic programming
- policy iteration
- infinite horizon
- stationary policies
- average cost
- average reward
- transition matrices
- reachability analysis
- finite horizon
- risk sensitive
- planning under uncertainty
- reinforcement learning algorithms
- markov chain
- markov decision process
- partially observable
- factored mdps
- decision processes
- decision theoretic planning
- model based reinforcement learning
- action sets
- optimal control
- state transitions
- reward function
- action space
- state and action spaces
- total reward