# L2E: Learning to Exploit Your Opponent

arXiv: https://arxiv.org/abs/2102.09381 · HTML: https://mlsanity.com/paper/2102.09381/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 48 references that are in the map.
- First posted on arXiv 18 Feb 2021.

## Builds on (most cited first, 9 of 9)

- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016)
- [Population Based Training of Neural Networks](https://mlsanity.com/paper/1711.09846/) (2017)
- [Human-level performance in first-person multiplayer games with population-based deep reinforcement learning](https://mlsanity.com/paper/1807.01281/) (2018)
- [Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions](https://mlsanity.com/paper/1901.01753/) (2019)
- [Wasserstein Robust Reinforcement Learning](https://mlsanity.com/paper/1907.13196/) (2019)
- [Unsupervised Meta-Learning for Reinforcement Learning](https://mlsanity.com/paper/1806.04640/) (2018)
- [Single Deep Counterfactual Regret Minimization](https://mlsanity.com/paper/1901.07621/) (2019)

## Abstract (arXiv)

Opponent modeling is essential to exploit sub-optimal opponents in strategic interactions. Most previous works focus on building explicit models to directly predict the opponents' styles or strategies, which require a large amount of data to train the model and lack adaptability to unknown opponents. In this work, we propose a novel Learning to Exploit (L2E) framework for implicit opponent modeling. L2E acquires the ability to exploit opponents by a few interactions with different opponents during training, thus can adapt to new opponents with unknown styles during testing quickly. We propose a novel opponent strategy generation algorithm that produces effective opponents for training automatically. We evaluate L2E on two poker games and one grid soccer game, which are the commonly used benchmarks for opponent modeling. Comprehensive experimental results indicate that L2E quickly adapts to diverse styles of unknown opponents.