Modelling The Dynamic Joint Policy Of Teammates With Attention Multi-agent DDPG

Abstract

Modelling and exploiting teammates' policies in cooperative multi-agent systems have long been an interest and also a big challenge for the reinforcement learning (RL) community. The interest lies in the fact that if the agent knows the teammates' policies, it can adjust its own policy accordingly to arrive at proper cooperations; while the challenge is that the agents' policies are changing continuously due to they are learning concurrently, which imposes difficulty to model the dynamic policies of teammates accurately. In this paper, we present *ATTention Multi-Agent Deep Deterministic Policy Gradient* (ATT-MADDPG) to address this challenge. ATT-MADDPG extends DDPG, a single-agent actor-critic RL method, with two special designs. First, in order to model the teammates' policies, the agent should get access to the observations and actions of teammates. ATT-MADDPG adopts a centralized critic to collect such information. Second, to model the teammates' policies using the collected infor

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keymao2018modelling

Related papers

• Padiff: Predictive And Adaptive Diffusion Policies For Ad Hoc Teamwork (2025)0.00
• Fast Teammate Adaptation In The Presence Of Sudden Policy Change (2023)0.00
• Policy Gradient With Self-attention For Model-free Distributed Nonlinear Multi-agent Games (2025)0.00
• 3DPG: Distributed Deep Deterministic Policy Gradient Algorithms For Networked Multi-agent Systems (2022)0.00
• Multi-agent Deep Reinforcement Learning With Extremely Noisy Observations (2018)0.00
• Multi-agent Cooperation Through Learning-aware Policy Gradients (2024)0.00
• Multi-agent Interactions Modeling With Correlated Policies (2020)2.60
• Parameter Sharing Deep Deterministic Policy Gradient For Cooperative Multi-agent Reinforcement Learning (2017)0.00