Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark.
Jiaming JiBorong ZhangJiayi ZhouXuehai PanWeidong HuangRuiyang SunYiran GengYifan ZhongJuntao DaiYaodong YangPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- model free
- learning algorithm
- state space
- unified model
- real world
- optimal policy
- robotic control
- temporal difference learning
- temporal difference
- transfer learning
- learning capabilities
- dynamic programming
- case study
- machine learning
- markov decision processes
- learning problems
- evaluation function
- database
- learning process
- knowledge base
- neural network
- policy search
- real time