Tleague: A Framework For Competitive Self-play Based Distributed Multi-agent Reinforcement Learning

Abstract

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 an

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysun2020tleague

Related papers

• Fightladder: A Benchmark For Competitive Multi-agent Reinforcement Learning (2024)0.00
• A Comprehensive Review Of Multi-agent Reinforcement Learning In Video Games (2025)5.24
• MARL-LNS: Cooperative Multi-agent Reinforcement Learning Via Large Neighborhoods Search (2024)0.00
• Reinforcing Competitive Multi-agents For Playing 'so Long Sucker' (2024)0.00
• Marllib: A Scalable And Efficient Multi-agent Reinforcement Learning Library (2022)0.00
• An Initial Introduction To Cooperative Multi-agent Reinforcement Learning (2024)0.00
• Local Advantage Networks For Cooperative Multi-agent Reinforcement Learning (2021)0.00
• MARSHAL: Incentivizing Multi-agent Reasoning Via Self-play With Strategic Llms (2025)0.00