# CURO: Curriculum Learning for Relative Overgeneralization

arXiv: https://arxiv.org/abs/2212.02733 · HTML: https://mlsanity.com/paper/2212.02733/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 6 Dec 2022.

## Builds on (most cited first, 23 of 23)

- [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)
- [QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1803.11485/) (2018)
- [Reinforcement Learning with Deep Energy-Based Policies](https://mlsanity.com/paper/1702.08165/) (2017)
- [The StarCraft Multi-Agent Challenge](https://mlsanity.com/paper/1902.04043/) (2019)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Value-Decomposition Networks For Cooperative Multi-Agent Learning](https://mlsanity.com/paper/1706.05296/) (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)
- [Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2006.10800/) (2020)
- [Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2109.11251/) (2021)
- [MAVEN: Multi-Agent Variational Exploration](https://mlsanity.com/paper/1910.07483/) (2019)
- [FACMAC: Factored Multi-Agent Centralised Policy Gradients](https://mlsanity.com/paper/2003.06709/) (2020)
- [Deep Coordination Graphs](https://mlsanity.com/paper/1910.00091/) (2019)
- [Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2102.03479/) (2021)
- [Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2102.04402/) (2021)
- [Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.10423/) (2020)
- [From Few to More: Large-scale Dynamic Multiagent Curriculum Learning](https://mlsanity.com/paper/1909.02790/) (2019)
- [UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2010.02974/) (2020)
- [Multiagent Soft Q-Learning](https://mlsanity.com/paper/1804.09817/) (2018)
- [Negative Update Intervals in Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1809.05096/) (2018)

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

- [Mitigating Relative Over-Generalization in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2411.11099/) (2024)

## Abstract (arXiv)

Relative overgeneralization (RO) is a pathology that can arise in cooperative multi-agent tasks when the optimal joint action's utility falls below that of a sub-optimal joint action. RO can cause the agents to get stuck into local optima or fail to solve cooperative tasks requiring significant coordination between agents within a given timestep. In this work, we empirically find that, in multi-agent reinforcement learning (MARL), both value-based and policy gradient MARL algorithms can suffer from RO and fail to learn effective coordination policies. To better overcome RO, we propose a novel approach called curriculum learning for relative overgeneralization (CURO). To solve a target task that exhibits strong RO, in CURO, we first fine-tune the reward function of the target task to generate source tasks to train the agent. Then, to effectively transfer the knowledge acquired in one task to the next, we use a transfer learning method that combines value function transfer with buffer transfer, which enables more efficient exploration in the target task. CURO is general and can be applied to both value-based and policy gradient MARL methods. We demonstrate that, when applied to QMIX, HAPPO, and HATRPO, CURO can successfully overcome severe RO, achieve improved performance, and outperform baseline methods in a variety of challenging cooperative multi-agent tasks.