Safety Enhancement for Deep Reinforcement Learning in Autonomous Separation Assurance.
Wei GuoMarc BrittainPeng WeiPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- autonomous learning
- function approximation
- cooperative
- learning capabilities
- state space
- optimal policy
- temporal difference learning
- image enhancement
- markov decision processes
- autonomous systems
- robotic systems
- transfer learning
- multi agent
- image processing
- robotic control
- nuclear power plant
- model free
- learning process
- reinforcement learning algorithms
- coal mining
- learning algorithm
- safety critical
- autonomous mental development
- function approximators
- action space
- deep learning
- temporal difference
- action selection
- contrast enhancement
- information security
- supervised learning
- dynamic programming