paper-with-me

홈 › Papers

TLeague: A Framework for Competitive Self-Play based Distributed Multi-Agent Reinforcement Learning

2020-11-25 · Peng Sun, Jiechao Xiong, Lei Han, Xinghai Sun, Shuxing Li, Jiawei Xu, Meng Fang, Zhengyou Zhang

Competitive Self-Play (CSP) based Multi-Agent Reinforcement Learning (MARL) has shown phenomenal breakthroughs recently. Strong AIs are achieved for several benchmarks, including Dota 2, Glory of Kings, Quake III, StarCraft II, to name a few. Despite the success, the MARL training is extremely data thirsty, requiring typically billions of (if not trillions of) frames be seen from the environment during training in order for learning a high performance agent. This poses non-trivial difficulties for researchers or engineers and prevents the application of MARL to a broader range of real-world problems. To address this issue, in this manuscript we describe a framework, referred to as TLeague, that aims at large-scale training and implements several main-stream CSP-MARL algorithms. The training can be deployed in either a single machine or a cluster of hybrid machines (CPUs and GPUs), where the standard Kubernetes is supported in a cloud native manner. TLeague achieves a high throughput and a reasonable scale-up when performing distributed training. Thanks to the modular design, it is also easy to extend for solving other multi-agent problems or implementing and verifying MARL algorithms. We present experiments over StarCraft II, ViZDoom and Pommerman to show the efficiency and effectiveness of TLeague. The code is open-sourced and available at https://github.com/tencent-ailab/tleague_projpage

📄 PDF Abstract BibTeX arXiv:2011.12895

Code (1)

tencent-ailab/tleague_projpage 공식 구현 tf

Tasks

Dota 2Multi-agent Reinforcement Learningreinforcement-learningReinforcement Learning (RL)StarcraftStarcraft II

Similar Papers 제목 키워드 기반

TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game

2020-11-27 · Lei Han, Jiechao Xiong, Peng Sun, Xinghai Sun 외

StarCraft, one of the most difficult esport games with long-standing history of professional tournaments, has attracted generations of players and fans, and also, intense attentions in artificial intelligence research. R…

AI AgentImitation LearningStarcraftStarcraft II

Offline Fictitious Self-Play for Competitive Games

2024-02-29 · Jingxiao Chen, Weiji Xie, Weinan Zhang, Yong Yu 외

Offline Reinforcement Learning (RL) has received significant interest due to its ability to improve policies in previously collected datasets without online interactions. Despite its success in the single-agent setting, …

Offline RLReinforcement Learning (RL)

Distributed Robust Subspace Recovery

2017-05-25 · Vahan Huroyan, Gilad Lerman

We propose distributed solutions to the problem of Robust Subspace Recovery (RSR). Our setting assumes a huge dataset in an ad hoc network without a central processor, where each node has access only to one chunk of the …

Minimax Exploiter: A Data Efficient Approach for Competitive Self-Play

2023-11-28 · Daniel Bairamian, Philippe Marcotte, Joshua Romoff, Gabriel Robert 외

Recent advances in Competitive Self-Play (CSP) have achieved, or even surpassed, human level performance in complex game environments such as Dota 2 and StarCraft II using Distributed Multi-Agent Reinforcement Learning (…

Atari GamesDiversityDota 2Multi-agent Reinforcement Learning+2

SPIRAL: Self-Play Incremental Racing Algorithm for Learning in Multi-Drone Competitions

2025-10-26 · Onur Akgün arxiv

This paper introduces SPIRAL (Self-Play Incremental Racing Algorithm for Learning), a novel approach for training autonomous drones in multi-agent racing competitions. SPIRAL distinctively employs a self-play mechanism t…

Reinforcement Learning