Offline Goal-Conditioned Reinforcement Learning for Safety-Critical Tasks with Recovery Policy.
Chenyang CaoZichen YanRenhao LuJunbo TanXueqian WangPublished in: ICRA (2024)
Keyphrases
- safety critical
- reinforcement learning
- optimal policy
- nuclear power plant
- formal methods
- real time
- agent learns
- embedded systems
- fault tolerant
- support systems
- safety analysis
- learning algorithm
- multi agent
- information systems
- intelligent agents
- agent architecture
- cooperative
- reinforcement learning algorithms
- markov decision process