Relational Q-Functionals: Multi-Agent Learning to Recover from Unforeseen Robot Malfunctions in Continuous Action Domains
2024 21ST INTERNATIONAL CONFERENCE ON UBIQUITOUS ROBOTS, UR 2024（2024）
关键词
Continuous Action,Continuous Domain,Multi-agent Reinforcement Learning,Network Of Relationships,Multi-agent Systems,Cooperative Strategy,Legged Robots,Neural Network,Learning Process,Behavioral Responses,Actual Values,Real-world Applications,Multilayer Perceptron,Individual Agency,Prediction Network,Cooperative Behavior,Markov Decision Process,Target Network,Independent Learning,Team Activities,Deep Q-network,Continuous Action Space,Trained Agent,Replay Memory
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要