Distribution-based objectives for Markov Decision Processes.
S. AkshayBlaise GenestNikhil VyasPublished in: LICS (2018)
Keyphrases
- markov decision processes
- optimal policy
- dynamic programming
- reinforcement learning
- finite state
- state space
- transition matrices
- policy iteration
- planning under uncertainty
- factored mdps
- model based reinforcement learning
- action sets
- infinite horizon
- average cost
- decision theoretic planning
- markov decision process
- reinforcement learning algorithms
- average reward
- reachability analysis
- state and action spaces
- finite horizon
- risk sensitive
- decision processes
- action space
- data mining
- machine learning