GTDE: Grouped Training with Decentralized Execution for Multi-agent Actor-Critic

December 12, 2024 Β· Declared Dead Β· πŸ› AAAI Conference on Artificial Intelligence

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Mengxian Li, Qi Wang, Yongjun Xu arXiv ID 2501.10367 Category cs.MA: Multiagent Systems Cross-listed cs.AI Citations 3 Venue AAAI Conference on Artificial Intelligence Last Checked 3 months ago
Abstract
The rapid advancement of multi-agent reinforcement learning (MARL) has given rise to diverse training paradigms to learn the policies of each agent in the multi-agent system. The paradigms of decentralized training and execution (DTDE) and centralized training with decentralized execution (CTDE) have been proposed and widely applied. However, as the number of agents increases, the inherent limitations of these frameworks significantly degrade the performance metrics, such as win rate, total reward, etc. To reduce the influence of the increasing number of agents on the performance metrics, we propose a novel training paradigm of grouped training decentralized execution (GTDE). This framework eliminates the need for a centralized module and relies solely on local information, effectively meeting the training requirements of large-scale multi-agent systems. Specifically, we first introduce an adaptive grouping module, which divides each agent into different groups based on their observation history. To implement end-to-end training, GTDE uses Gumbel-Sigmoid for efficient point-to-point sampling on the grouping distribution while ensuring gradient backpropagation. To adapt to the uncertainty in the number of members in a group, two methods are used to implement a group information aggregation module that merges member information within the group. Empirical results show that in a cooperative environment with 495 agents, GTDE increased the total reward by an average of 382\% compared to the baseline. In a competitive environment with 64 agents, GTDE achieved a 100\% win rate against the baseline.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Multiagent Systems

Died the same way β€” πŸ‘» Ghosted