Dominance-constrained Markov decision processes.
William B. HaskellRahul JainPublished in: CDC (2012)
Keyphrases
- markov decision processes
- finite state
- optimal policy
- transition matrices
- reinforcement learning
- state space
- dynamic programming
- reachability analysis
- decision processes
- reinforcement learning algorithms
- policy iteration
- model based reinforcement learning
- finite horizon
- decision theoretic planning
- action space
- planning under uncertainty
- risk sensitive
- partially observable
- factored mdps
- infinite horizon
- average reward
- state and action spaces
- total reward
- markov decision process
- data mining
- average cost
- reward function
- multistage
- learning algorithm
- machine learning