On the Robustness of Safe Reinforcement Learning under Observational Perturbations.
Zuxin LiuZijian GuoZhepeng CenHuan ZhangJie TanBo LiDing ZhaoPublished in: ICLR (2023)
Keyphrases
- reinforcement learning
- function approximation
- multi agent
- state space
- computational efficiency
- markov decision processes
- temporal difference
- reinforcement learning algorithms
- direct policy search
- real time
- neural network
- real world
- learning algorithm
- high robustness
- multi agent reinforcement learning
- robotic control