# Improving generalization in reinforcement learning through forked agents

arXiv: https://arxiv.org/abs/2212.06451 · HTML: https://mlsanity.com/paper/2212.06451/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 20 references that are in the map.
- First posted on arXiv 13 Dec 2022.

## Builds on (most cited first, 15 of 15)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Leveraging Procedural Generation to Benchmark Reinforcement Learning](https://mlsanity.com/paper/1912.01588/) (2019)
- [Quantifying Generalization in Reinforcement Learning](https://mlsanity.com/paper/1812.02341/) (2018)
- [Assessing Generalization in Deep Reinforcement Learning](https://mlsanity.com/paper/1810.12282/) (2018)
- [Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck](https://mlsanity.com/paper/1910.12911/) (2019)
- [Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation](https://mlsanity.com/paper/1806.10729/) (2018)
- [Gotta Learn Fast: A New Benchmark for Generalization in RL](https://mlsanity.com/paper/1804.03720/) (2018)
- [Divide-and-Conquer Reinforcement Learning](https://mlsanity.com/paper/1711.09874/) (2017)
- [Invariant Policy Optimization: Towards Stronger Generalization in Reinforcement Learning](https://mlsanity.com/paper/2006.01096/) (2020)
- [Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning](https://mlsanity.com/paper/2008.00614/) (2020)
- [Improving Policy Optimization with Generalist-Specialist Learning](https://mlsanity.com/paper/2206.12984/) (2022)
- [Improving Performance in Reinforcement Learning by Breaking Generalization in Neural Networks](https://mlsanity.com/paper/2003.07417/) (2020)
- [Reinforcement Learning Generalization with Surprise Minimization](https://mlsanity.com/paper/2004.12399/) (2020)
- [Weight Initialization Techniques for Deep Learning Algorithms in Remote Sensing: Recent Trends and Future Perspectives](https://mlsanity.com/paper/2102.07004/) (2021)

## Abstract (arXiv)

An eco-system of agents each having their own policy with some, but limited, generalizability has proven to be a reliable approach to increase generalization across procedurally generated environments. In such an approach, new agents are regularly added to the eco-system when encountering a new environment that is outside of the scope of the eco-system. The speed of adaptation and general effectiveness of the eco-system approach highly depends on the initialization of new agents. In this paper we propose different initialization techniques, inspired from Deep Neural Network initialization and transfer learning, and study their impact.