# Overcoming Environmental Meta-Stationarity in MARL via Adaptive Curriculum and Counterfactual Group Advantage

arXiv: https://arxiv.org/abs/2506.07548 · HTML: https://mlsanity.com/paper/2506.07548/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 49 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Builds on (most cited first, 26 of 26)

- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (2017)
- [Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.08839/) (2020)
- [QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1905.05408/) (2019)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [QPLEX: Duplex Dueling Multi-Agent Q-Learning](https://mlsanity.com/paper/2008.01062/) (2020)
- [Google Research Football: A Novel Reinforcement Learning Environment](https://mlsanity.com/paper/1907.11180/) (2019)
- [Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks](https://mlsanity.com/paper/2006.07869/) (2020)
- [Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2006.10800/) (2020)
- [Automatic Curriculum Learning For Deep RL: A Short Survey](https://mlsanity.com/paper/2003.04664/) (2020)
- [SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2212.07489/) (2022)
- [A Survey of Multi-Agent Deep Reinforcement Learning with Communication](https://mlsanity.com/paper/2203.08975/) (2022)
- [A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity](https://mlsanity.com/paper/1707.09183/) (2017)
- [A Survey of Reinforcement Learning Algorithms for Dynamically Varying Environments](https://mlsanity.com/paper/2005.10619/) (2020)
- [An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2409.03052/) (2024)
- [Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration](https://mlsanity.com/paper/2111.11032/) (2021)
- [From Few to More: Large-scale Dynamic Multiagent Curriculum Learning](https://mlsanity.com/paper/1909.02790/) (2019)
- [A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectives](https://mlsanity.com/paper/2503.13415/) (2025)
- [The Neural MMO Platform for Massively Multiagent Research](https://mlsanity.com/paper/2110.07594/) (2021)
- [TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game](https://mlsanity.com/paper/1809.07193/) (2018)
- [Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learning](https://mlsanity.com/paper/2302.02792/) (2023)
- [Scalable Communication for Multi-Agent Reinforcement Learning via Transformer-Based Email Mechanism](https://mlsanity.com/paper/2301.01919/) (2023)
- [Dealing with Non-Stationarity in MARL via Trust-Region Decomposition](https://mlsanity.com/paper/2102.10616/) (2021)
- [MARLens: Understanding Multi-agent Reinforcement Learning for Traffic Signal Control via Visual Analytics](https://mlsanity.com/paper/2410.01364/) (2024)
- [Deep Q-Network Based Multi-agent Reinforcement Learning with Binary Action Agents](https://mlsanity.com/paper/2008.04109/) (2020)

## Built on by (most cited first, 1 of 1)

- [Counterfactual Credit Policy Optimization for Multi-Agent Collaboration](https://mlsanity.com/paper/2603.21563/) (2026)

## Abstract (arXiv)

Multi-agent reinforcement learning (MARL) has reached competitive performance on cooperative tasks against scripted adversaries, yet most methods train agents at a single fixed difficulty throughout the entire run. We term this static-difficulty regime environmental meta-stationarity and show that it caps policy generalization and steers learning toward shallow local optima. To break this regime, we propose CL-MARL, a dynamic curriculum learning framework that adapts opponent strength online from win-rate signals, advancing or regressing the task as agents master it. Its scheduler, FlexDiff, fuses momentum-based trend estimation with sliding-window dual-curve monitoring of training and evaluation returns, yielding stable difficulty transitions without manual tuning. Because a moving curriculum amplifies non-stationarity and sparsifies global rewards, we introduce the Counterfactual Group Relative Policy Advantage (CGRPA), which extends GRPO-style group-relative optimization with counterfactual baselines to disentangle each agent's contribution under shifting team dynamics. On the StarCraft Multi-Agent Challenge (SMAC), CL-MARL attains a 40% mean win rate on the super-hard maps with an average episode return of 17.85, exceeding the QMIX, OW-QMIX, DER, EMC, and MARR baselines by +2.94 on average, while reaching its peak win rate roughly 1.28faster on 8m_vs_9m and 1.42 faster on 3s5z_vs_3s6z than the strongest baseline. The implementation is publicly available at https://github.com/NICE-HKU/CL2MARL-SMAC.