Constrained Discounted Markov Decision Processes and Hamiltonian Cycles.
Eugene A. FeinbergPublished in: Math. Oper. Res. (2000)
Keyphrases
- markov decision processes
- state space
- optimal policy
- infinite horizon
- average cost
- finite state
- dynamic programming
- policy iteration
- transition matrices
- decision theoretic planning
- average reward
- reinforcement learning
- partially observable
- model based reinforcement learning
- factored mdps
- finite horizon
- reachability analysis
- decision processes
- planning under uncertainty
- markov decision process
- discounted reward
- action space
- reinforcement learning algorithms
- semi markov decision processes
- risk sensitive
- machine learning
- sufficient conditions
- total reward
- reward function
- data mining