Iterative Reachability Estimation for Safe Reinforcement Learning.
Milan GanaiZheng GongChenning YuSylvia L. HerbertSicun GaoPublished in: NeurIPS (2023)
Keyphrases
- reinforcement learning
- state space
- decision directed
- genetic algorithm
- probability distribution
- parameter estimation
- optimal policy
- markov decision processes
- function approximation
- learning algorithm
- knowledge base
- learning process
- data sets
- maximum likelihood estimation
- robot control
- multi agent reinforcement learning
- database