Safe Exploration in Markov Decision Processes
Teodor Mihai MoldovanPieter AbbeelPublished in: CoRR (2012)
Keyphrases
- markov decision processes
- model based reinforcement learning
- interval estimation
- dynamic programming
- state space
- optimal policy
- finite state
- policy iteration
- reinforcement learning
- transition matrices
- average reward
- decision theoretic planning
- reachability analysis
- reinforcement learning algorithms
- partially observable
- action space
- infinite horizon
- average cost
- planning under uncertainty
- factored mdps
- markov decision process
- decision processes
- risk sensitive
- action sets
- machine learning
- semi markov decision processes