Logistic Markov Decision Processes.
Martin MladenovCraig BoutilierDale SchuurmansOfer MeshiGal ElidanTyler LuPublished in: IJCAI (2017)
Keyphrases
- markov decision processes
- state space
- optimal policy
- finite state
- dynamic programming
- reinforcement learning
- reachability analysis
- partially observable
- infinite horizon
- average cost
- risk sensitive
- transition matrices
- decision theoretic planning
- planning under uncertainty
- finite horizon
- reinforcement learning algorithms
- average reward
- action space
- policy iteration
- factored mdps
- model based reinforcement learning
- state and action spaces
- decision diagrams
- action sets
- reward function
- markov chain