OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research.
Jiaming JiJiayi ZhouBorong ZhangJuntao DaiXuehai PanRuiyang SunWeidong HuangYiran GengMickel LiuYaodong YangPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- robotic control
- temporal difference learning
- dynamic programming
- state space
- optimal policy
- highly distributed
- multi agent reinforcement learning
- data collection
- temporal difference
- information exchange
- model free
- optimal control
- support environment
- markov decision processes
- learning algorithm
- machine learning
- real time
- markov decision process
- learning agent
- action space
- learning agents
- supervised learning
- multi agent
- information retrieval