Actor-Attention-Critic for Multi-Agent Reinforcement Learning
This method addresses multi-agent learning problems for applications in cooperative, individualized, and adversarial settings, offering flexibility without assumptions about action spaces or global states.
The paper tackles the challenge of multi-agent reinforcement learning by introducing an actor-critic algorithm with a centralized attention mechanism that selects relevant information for each agent, enabling more effective and scalable learning in complex environments compared to recent approaches.
Reinforcement learning in multi-agent scenarios is important for real-world applications but presents challenges beyond those seen in single-agent settings. We present an actor-critic algorithm that trains decentralized policies in multi-agent settings, using centrally computed critics that share an attention mechanism which selects relevant information for each agent at every timestep. This attention mechanism enables more effective and scalable learning in complex multi-agent environments, when compared to recent approaches. Our approach is applicable not only to cooperative settings with shared rewards, but also individualized reward settings, including adversarial settings, as well as settings that do not provide global states, and it makes no assumptions about the action spaces of the agents. As such, it is flexible enough to be applied to most multi-agent learning problems.