Learning From Oracle Demonstrations - A New Approach to Develop Autonomous Intersection Management Control Algorithms Based on Multiagent Deep Reinforcement Learning.
Antonio Guillen-PerezMaría-Dolores CanoPublished in: IEEE Access (2022)
Keyphrases
- reinforcement learning
- learning algorithm
- multi agent
- learning process
- learning agents
- autonomous learning
- reinforcement learning methods
- learning capabilities
- action selection
- multiagent learning
- rl algorithms
- control problems
- optimal control
- cooperative
- computational complexity
- learning tasks
- distributed constraint optimization
- information systems
- noise tolerant
- supervised learning
- active learning
- partially observable domains
- learning models
- active exploration
- control policies
- deep learning
- robot control
- data management
- database
- model free