FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning

2024-06-04 · Wenzhe Li, Zihan Ding, Seth Karten, Chi Jin

Recent advances in reinforcement learning (RL) heavily rely on a variety of well-designed benchmarks, which provide environmental platforms and consistent criteria to evaluate existing and novel algorithms. Specifically, in multi-agent RL (MARL), a plethora of benchmarks based on cooperative games have spurred the development of algorithms that improve the scalability of cooperative multi-agent systems. However, for the competitive setting, a lightweight and open-sourced benchmark with challenging gaming dynamics and visual inputs has not yet been established. In this work, we present FightLadder, a real-time fighting game platform, to empower competitive MARL research. Along with the platform, we provide implementations of state-of-the-art MARL algorithms for competitive games, as well as a set of evaluation metrics to characterize the performance and exploitability of agents. We demonstrate the feasibility of this platform by training a general agent that consistently defeats 12 built-in characters in single-player mode, and expose the difficulty of training a non-exploitable agent without human knowledge and demonstrations in two-player mode. FightLadder provides meticulously designed environments to address critical challenges in competitive MARL research, aiming to catalyze a new era of discovery and advancement in the field. Videos and code at https://sites.google.com/view/fightladder/home.

📄 PDF Abstract BibTeX arXiv:2406.02081

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

For How Long Should We Be Punching? Learning Action Duration in Fighting Games

2026-05-20 · Hoang Hai Nguyen, Kurt Driessens, Dennis J. N. J. Soemers arxiv

Fighting games such as Street Fighter II present unique challenges to reinforcement learning (RL) agents due to their fast-paced, real-time nature. In most RL frameworks, agents are hard-coded to make decisions at a fixe…

Reinforcement Learning

A Framework for Scalable Heterogeneous Multi-Agent Adversarial Reinforcement Learning in IsaacLab

2025-09-26 · Isaac Peterson, Christopher Allred, Jacob Morrey, Mario Harper arxiv

Multi-Agent Reinforcement Learning (MARL) is central to robotic systems cooperating in dynamic environments. While prior work has focused on these collaborative settings, adversarial interactions are equally critical for…

Multi-agent Reinforcement Learning

Memory-Induced Supra-Competitive Outcomes Between Deep Reinforcement Learning Agents in Optimal Trade Execution

2026-05-19 · Christos Spyridon Koulouris, Carlo Campajola arxiv

In this paper, we investigate whether deep reinforcement-learning agents interacting in a shared optimal-execution environment can sustain supra-competitive outcomes, in the sense of achieving lower implementation shortf…

Reinforcement Learning

Individual Control Barrier Functions-Guided Diffusion Model for Safe Offline Multi-Agent Reinforcement Learning

2026-06-10 · Qingyun Guo, Junyi Shi, Jianuo Huang, Tianyu Shi arxiv

Offline reinforcement learning allows control policies to be learned directly from data without online interaction, making it suitable for safety-critical tasks. Recent studies have applied diffusion models to offline re…

Multi-agent Reinforcement Learning

CoMaTrack: Competitive Multi-Agent Game-Theoretic Tracking with Vision-Language-Action Models

2026-03-24 · Youzhi Liu, Li Gao, Liu Liu, Mingyang Lv 외 arxiv

Embodied Visual Tracking (EVT), a core dynamic task in embodied intelligence, requires an agent to precisely follow a language-specified target. Yet most existing methods rely on single-agent imitation learning, sufferin…

Multi-agent Reinforcement Learning Visual Tracking