{"ID":2888847,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.22782","arxiv_id":"2507.22782","title":"Enhancing Multi-Agent Collaboration with Attention-Based Actor-Critic Policies","abstract":"This paper introduces Team-Attention-Actor-Critic (TAAC), a reinforcement learning algorithm designed to enhance multi-agent collaboration in cooperative environments. TAAC employs a Centralized Training/Centralized Execution scheme incorporating multi-headed attention mechanisms in both the actor and critic. This design facilitates dynamic, inter-agent communication, allowing agents to explicitly query teammates, thereby efficiently managing the exponential growth of joint-action spaces while ensuring a high degree of collaboration. We further introduce a penalized loss function which promotes diverse yet complementary roles among agents. We evaluate TAAC in a simulated soccer environment against benchmark algorithms representing other multi-agent paradigms, including Proximal Policy Optimization and Multi-Agent Actor-Attention-Critic. We find that TAAC exhibits superior performance and enhanced collaborative behaviors across a variety of metrics (win rates, goal differentials, Elo ratings, inter-agent connectivity, balanced spatial distributions, and frequent tactical interactions such as ball possession swaps).","short_abstract":"This paper introduces Team-Attention-Actor-Critic (TAAC), a reinforcement learning algorithm designed to enhance multi-agent collaboration in cooperative environments. TAAC employs a Centralized Training/Centralized Execution scheme incorporating multi-headed attention mechanisms in both the actor and critic. This desi...","url_abs":"https://arxiv.org/abs/2507.22782","url_pdf":"https://arxiv.org/pdf/2507.22782v3","authors":"[\"Hugo Garrido-Lestache Belinchon\",\"Jeremy Kedziora\"]","published":"2025-07-30T15:48:38Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.LG\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}