Technical Note - An Equivalence Between Continuous and Discrete Time Markov Decision Processes.
Richard F. SerfozoPublished in: Oper. Res. (1979)
Keyphrases
- markov decision processes
- finite state
- action space
- semi markov decision processes
- state space
- optimal policy
- reinforcement learning
- continuous state spaces
- policy iteration
- dynamic programming
- reachability analysis
- stationary policies
- average reward
- transition matrices
- decision diagrams
- decision theoretic planning
- partially observable
- finite horizon
- factored mdps
- model based reinforcement learning
- average cost
- planning under uncertainty
- infinite horizon
- markov chain
- state and action spaces
- markov decision process
- risk sensitive
- decision processes
- state abstraction
- continuous state
- action sets
- least squares
- optimal solution
- machine learning