Accretive Operators and Markov Decision Processes.
Stanley R. PliskaPublished in: Math. Oper. Res. (1980)
Keyphrases
- markov decision processes
- transition matrices
- dynamic programming
- optimal policy
- state space
- finite state
- reinforcement learning
- policy iteration
- decision theoretic planning
- planning under uncertainty
- decision diagrams
- infinite horizon
- reinforcement learning algorithms
- factored mdps
- average cost
- reachability analysis
- semi markov decision processes
- partially observable
- action sets
- risk sensitive
- decision processes
- average reward
- decision problems
- markov decision process
- reward function
- finite horizon
- partially observable markov decision processes
- machine learning