Online Learning of Safety function for Markov Decision Processes.
Abhijit MazumdarRafal WisniewskiManuela-Luminita BujorianuPublished in: ECC (2023)
Keyphrases
- markov decision processes
- online learning
- optimal policy
- finite state
- state space
- policy iteration
- reinforcement learning
- dynamic programming
- transition matrices
- decision theoretic planning
- reinforcement learning algorithms
- infinite horizon
- average reward
- average cost
- decision processes
- reachability analysis
- partially observable
- model based reinforcement learning
- state and action spaces
- factored mdps
- e learning
- planning under uncertainty
- finite horizon
- risk sensitive
- semi markov decision processes
- reward function
- dynamical systems