Physical Deep Reinforcement Learning Towards Safety Guarantee.
Hongpeng CaoYanbing MaoLui ShaMarco CaccamoPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- learning algorithm
- state space
- temporal difference
- model free
- robotic control
- real time
- stochastic approximation
- physical world
- markov decision processes
- machine learning
- united states
- optimal control
- optimal policy
- least squares
- active learning
- reinforcement learning algorithms
- safety critical
- multi agent reinforcement learning
- safety analysis
- data sets