Finite-State Approximations to Discounted and Average Cost Constrained Markov Decision Processes.
Naci SaldiPublished in: IEEE Trans. Autom. Control. (2019)
Keyphrases
- finite state
- average cost
- markov decision processes
- optimal policy
- finite horizon
- state space
- policy evaluation
- infinite horizon
- approximate dynamic programming
- reinforcement learning
- policy iteration
- risk sensitive
- action sets
- markov decision chains
- markov decision process
- initial state
- reinforcement learning algorithms
- partially observable
- decision processes
- average reward
- dynamic programming
- approximation methods
- markov chain
- action space
- machine learning
- decision problems
- stationary policies
- model checking
- data mining