Adaptive cooperative exploration for reinforcement learning from imperfect demonstrations.
Fuxian HuangNaye JiHuajian NiShijian LiXi LiPublished in: Pattern Recognit. Lett. (2023)
Keyphrases
- cooperative
- reinforcement learning
- multi agent reinforcement learning
- multi agent
- function approximation
- action selection
- active exploration
- machine learning
- exploration exploitation
- adaptive control
- model based reinforcement learning
- exploration strategy
- autonomous learning
- real time
- multi agent systems
- model free
- markov decision processes
- reinforcement learning algorithms
- partially observable
- learning agents
- distributed problem solving
- state space
- dynamic programming
- hidden markov models
- multiagent reinforcement learning
- information systems
- robotic control
- data sets