Search results with tag "Multi agent reinforcement"

Actor-Attention-Critic for Multi-Agent Reinforcement …

reinforcement learning does not take these dynamics into account, instead simply considering all agents at all time-points. Our attention critic is able to dynamically select which agents to attend to at each time point during train-ing, improving performance in multi-agent domains with complex interactions.

  Multi, Learning, Agent, Reinforcement, Reinforcement learning, Multi agent reinforcement