Google Research Football

'Google Research Football' is a benchmark that contains a simulated football environment used to evaluate cooperative multi-agent reinforcement learning (MARL) algorithms in complex, dynamic settings.

Papers using Google Research Football (19)

Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning2025 · 3 citesSPECTra: Scalable Multi-Agent Reinforcement Learning with Permutation-Free Networks2025 · 2 citesLanguage-Driven Coordination and Learning in Multi-Agent Simulation Environments2025 · 1 citesMARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning2026Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus2026Dual-Gated Epistemic Time-Dilation: Autonomous Compute Modulation in Asynchronous MARL2026Multi-Agent Deep Reinforcement Learning Under Constrained Communications2026Predictive Auxiliary Learning for Belief-based Multi-Agent Systems2025Redistributing Rewards Across Time and Agents for Multi-Agent Reinforcement Learning2025Vision-Based Generic Potential Function for Policy Alignment in Multi-Agent Reinforcement Learning2025PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning2025Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning2024 · 3 citesMARL-LNS: Cooperative Multi-agent Reinforcement Learning via Large Neighborhoods Search2024 · 1 citesLAGMA: LAtent Goal-guided Multi-Agent Reinforcement Learning2024 · 1 citesLeveraging Team Correlation for Approximating Equilibrium in Two-Team Zero-Sum Games2024Heterogeneous Multi-Agent Reinforcement Learning for Zero-Shot Scalable Collaboration2024Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning2024B2MAPO: A Batch-by-Batch Multi-Agent Policy Optimization to Balance Performance and Efficiency2024Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning2024