An axiomatic approach to Markov decision processes.
Adam JonssonPublished in: Math. Methods Oper. Res. (2023)
Keyphrases
- markov decision processes
- optimal policy
- finite state
- state space
- transition matrices
- policy iteration
- factored mdps
- average cost
- reinforcement learning
- decision theoretic planning
- infinite horizon
- dynamic programming
- risk sensitive
- partially observable
- action space
- planning under uncertainty
- reinforcement learning algorithms
- model based reinforcement learning
- finite horizon
- markov decision process
- average reward
- action sets
- policy evaluation
- sufficient conditions
- markov chain
- state and action spaces
- least squares