Efficient and Safe Exploration in Deterministic Markov Decision Processes with Unknown Transition Models.
Erdem BiyikJonathan MargoliashShahrouz Ryan AlimoDorsa SadighPublished in: CoRR (2019)
Keyphrases
- markov decision processes
- transition matrices
- reinforcement learning
- model based reinforcement learning
- state space
- optimal policy
- dynamic programming
- decision theoretic planning
- planning under uncertainty
- finite state
- interval estimation
- reachability analysis
- factored mdps
- risk sensitive
- average reward
- transition model
- partially observable
- reinforcement learning algorithms
- real valued
- probabilistic model