# Safe adaptation in multiagent competition

arXiv: https://arxiv.org/abs/2203.07562 · HTML: https://mlsanity.com/paper/2203.07562/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 40 references that are in the map.
- First posted on arXiv 14 Mar 2022.

## Builds on (most cited first, 28 of 28)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning](https://mlsanity.com/paper/1803.11347/) (2018)
- [Towards Continual Reinforcement Learning: A Review and Perspectives](https://mlsanity.com/paper/2012.13490/) (2020)
- [A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning](https://mlsanity.com/paper/1711.00832/) (2017)
- [Human-level performance in first-person multiplayer games with population-based deep reinforcement learning](https://mlsanity.com/paper/1807.01281/) (2018)
- [Learning with Opponent-Learning Awareness](https://mlsanity.com/paper/1709.04326/) (2017)
- [Adversarial Policies: Attacking Deep Reinforcement Learning](https://mlsanity.com/paper/1905.10615/) (2019)
- [FACMAC: Factored Multi-Agent Centralised Policy Gradients](https://mlsanity.com/paper/2003.06709/) (2020)
- [Emergent Complexity via Multi-Agent Competition](https://mlsanity.com/paper/1710.03748/) (2017)
- [Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments](https://mlsanity.com/paper/1710.03641/) (2017)
- [Opponent Modeling in Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05559/) (2016)
- [Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL](https://mlsanity.com/paper/1812.07671/) (2018)
- [Modeling Others using Oneself in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1802.09640/) (2018)
- [Real World Games Look Like Spinning Tops](https://mlsanity.com/paper/2004.09468/) (2020)
- [Robust Reinforcement Learning using Adversarial Populations](https://mlsanity.com/paper/2008.01825/) (2020)
- [Learning Policy Representations in Multiagent Systems](https://mlsanity.com/paper/1806.06464/) (2018)
- [Safe and Nested Subgame Solving for Imperfect-Information Games](https://mlsanity.com/paper/1705.02955/) (2017)
- [A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning](https://mlsanity.com/paper/2011.00382/) (2020)
- [Generalized Proximal Policy Optimization with Sample Reuse](https://mlsanity.com/paper/2111.00072/) (2021)
- [Diversity-Inducing Policy Gradient: Using Maximum Mean Discrepancy to Find a Set of Diverse Policies](https://mlsanity.com/paper/1906.00088/) (2019)
- [Variational Autoencoders for Opponent Modeling in Multi-Agent Systems](https://mlsanity.com/paper/2001.10829/) (2020)
- [Policy Search by Target Distribution Learning for Continuous Control](https://mlsanity.com/paper/1905.11041/) (2019)

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

- [Structured Diversity Control: A Dual-Level Framework for Group-Aware Multi-Agent Coordination](https://mlsanity.com/paper/2506.18651/) (2025)

## Abstract (arXiv)

Achieving the capability of adapting to ever-changing environments is a critical step towards building fully autonomous robots that operate safely in complicated scenarios. In multiagent competitive scenarios, agents may have to adapt to new opponents with previously unseen behaviors by learning from the interaction experiences between the ego-agent and the opponent. However, this adaptation is susceptible to opponent exploitation. As the ego-agent updates its own behavior to exploit the opponent, its own behavior could become more exploitable as a result of overfitting to this specific opponent's behavior. To overcome this difficulty, we developed a safe adaptation approach in which the ego-agent is trained against a regularized opponent model, which effectively avoids overfitting and consequently improves the robustness of the ego-agent's policy. We evaluated our approach in the Mujoco domain with two competing agents. The experiment results suggest that our approach effectively achieves both adaptation to the specific opponent that the ego-agent is interacting with and maintaining low exploitability to other possible opponent exploitation.