Average Optimality for Continuous-Time Markov Decision Processes Under Weak Continuity Conditions.
Yi ZhangPublished in: J. Appl. Probab. (2014)
Keyphrases
- markov decision processes
- stationary policies
- average cost
- state space
- action sets
- finite state
- markov decision process
- optimal policy
- optimal control
- reinforcement learning
- sufficient conditions
- dynamic programming
- linear program
- transition matrices
- partially observable
- reachability analysis
- infinite horizon
- policy iteration
- decision theoretic planning
- average reward
- action space
- finite horizon
- long run
- decision processes
- lot sizing
- reinforcement learning algorithms
- finite number
- initial state
- factored mdps
- model based reinforcement learning
- fixed point
- convergence rate
- planning under uncertainty
- markov decision problems
- risk sensitive
- reward function
- state and action spaces
- monte carlo
- discounted reward
- function approximation
- interval estimation