A GENERAL METHOD FOR MULTI-AGENT REINFORCEMENT LEARNING IN UNRESTRICTED ENVIRONMENTS

By J. Schmidhuber. 1996

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Peter Stone
2. Yaodong Yang
3. Manuela M. Veloso
4. Gerhard Weiss
5. Yen-Cheng Liu
6. Ying Wen
7. Jun Wang
8. Sandip Sen

Citations in the corpus

• Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games (2017, background): “The studies on interaction and collaboration in multiagent settings have a long history (Littman 1994; Schmidhuber 1996).”
• Who2com: Collaborative Perception via Learnable Handshake Communication (2020, background): “Existing works on MARL demonstrated the effectiveness of communication for various tasks, applying the models on simplistic 2D grid environments where the observation of each agent is low-dimensional.”
• Learning in multiagent systems (1999, background): “Recent work on theoretical and experimental issues in multiagent reinforcement learning promises new frameworks for isolated and interactive learning of coordination (e.g., [1, 11, 19, 42 , 64]).”
• Multiagent Bidirectionally-Coordinated Nets for Learning to Play StarCraft Combat Games (2017, methodology): “As function approximators, neural networks have also been adopted and proven to be effective and flexible [18].”
• Multiagent Systems: A Survey from a Machine Learning Perspective (2000, background): “Don't model others–just pay attention to reward (Schmidhuber, 1996).”