APC: Predict Global Representation From Local Observation In Multi-Agent Reinforcement Learning
Primary Area: reinforcement learning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Multi-Agent Reinforcement Learning, Centralized Training and Decentralized Execution, Multi-Agent Cooperation, Multi-Agent Systerms
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: We propose the actor-predict-critic (APC) algorithm where actor learns to predict global representation from local observation to sovle multi-agent cooperation tasks.
Abstract: Multi-agent reinforcement learning (MARL) algorithms with sequential decision-making strategies have achieved great success in cooperation tasks recently. To overcome the non-stationarity problem, these methods design a centralized controller that takes global observation as input and chooses actions for each agent in sequence. However, in most scenarios, global information is only available at training time, while agents act synchronously with their local observation at execution time, which prevents agents from leveraging more information in cooperation. In this paper, based on actor-critic architecture, we propose the actor-predicts-critic (APC) algorithm, in which the actor learns to predict the global representations of centralized critic from local observation. During the training, the actor not only receives the estimated state values, but also takes the critic's representations that are extracted from global information as the prediction targets. Since these global representations are closely related to agents' goals and rewards, agents can achieve better cooperation on MARL tasks utilizing the predicted representations. To prove the validity of APC, we evaluate the algorithm on StarCraft2, Google Research Football, and Multi-Agent Mujoco benchmarks. The results show that APC significantly outperforms the strong baselines in centralized training and decentralized execution (CTDE) framework, including MAT-Dec, MAPPO, and fine-tuned QMIX.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 1624
Loading