Multi-Agent MuJoCo

'Multi-Agent MuJoCo' is a benchmark that contains a variety of cooperative multi-agent environments used to evaluate the performance and coordination of algorithms in addressing challenges associated with large joint observation and action spaces in multi-agent reinforcement learning.

Papers using Multi-Agent MuJoCo (14)

AOAD-MAT: Transformer-based multi-agent deep reinforcement learning model considering agents' order of action decisions2025 · 1 citesMulti-Agent Model-Based Reinforcement Learning with Joint State-Action Learned Embeddings2026Multi-Agent Deep Reinforcement Learning Under Constrained Communications2026A Historical Interaction-Enhanced Shapley Policy Gradient Algorithm for Multi-Agent Credit Assignment2025HCPO: Hierarchical Conductor-Based Policy Optimization in Multi-Agent Reinforcement Learning2025$K$-Level Policy Gradients for Multi-Agent Reinforcement Learning2025Offline Multi-agent Reinforcement Learning via Score Decomposition2025Oryx: a Scalable Sequence Model for Many-Agent Coordination in Offline MARL2025SrSv: Integrating Sequential Rollouts with Sequential Value Estimation for Multi-agent Reinforcement Learning2025 · 2 citesKaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning2024 · 1 citesComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization2024PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning2025Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation2025Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus2026