# Genetic Drift Regularization: on preventing Actor Injection from breaking Evolution Strategies

arXiv: https://arxiv.org/abs/2405.04322 · HTML: https://mlsanity.com/paper/2405.04322/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods.
- Builds on 16 of its 39 references that are in the map.
- First posted on arXiv 7 May 2024.

## Placed in

- Deep reinforcement learning methods / [RL for games and combinatorial optimization](https://mlsanity.com/deeprl/rl-for-games-and-combinatorial-optimization/)

## Builds on (most cited first, 16 of 16)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation](https://mlsanity.com/paper/2106.13281/) (2021)
- [Evolution-Guided Policy Gradient in Reinforcement Learning](https://mlsanity.com/paper/1805.07917/) (2018)
- [CEM-RL: Combining evolutionary and gradient-based methods for policy search](https://mlsanity.com/paper/1810.01222/) (2018)
- [evosax: JAX-based Evolution Strategies](https://mlsanity.com/paper/2212.04180/) (2022)
- [Proximal Distilled Evolutionary Reinforcement Learning](https://mlsanity.com/paper/1906.09807/) (2019)
- [Combining Evolution and Deep Reinforcement Learning for Policy Search: a Survey](https://mlsanity.com/paper/2203.14009/) (2022)
- [ERL-Re2: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation](https://mlsanity.com/paper/2210.17375/) (2022)
- [A Surrogate-Assisted Controller for Expensive Evolutionary Reinforcement Learning](https://mlsanity.com/paper/2201.00129/) (2022)
- [Understanding the Synergies between Quality-Diversity and Deep Reinforcement Learning](https://mlsanity.com/paper/2303.06164/) (2023)
- [Rethinking Population-assisted Off-policy Reinforcement Learning](https://mlsanity.com/paper/2305.02949/) (2023)
- [Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability](https://mlsanity.com/paper/2306.00045/) (2023)

## Abstract (arXiv)

Evolutionary Algorithms (EA) have been successfully used for the optimization of neural networks for policy search, but they still remain sample inefficient and underperforming in some cases compared to gradient-based reinforcement learning (RL). Various methods combine the two approaches, many of them training a RL algorithm on data from EA evaluations and injecting the RL actor into the EA population. However, when using Evolution Strategies (ES) as the EA, the RL actor can drift genetically far from the the ES distribution and injection can cause a collapse of the ES performance. Here, we highlight the phenomenon of genetic drift where the actor genome and the ES population distribution progressively drift apart, leading to injection having a negative impact on the ES. We introduce Genetic Drift Regularization (GDR), a simple regularization method in the actor training loss that prevents the actor genome from drifting away from the ES. We show that GDR can improve ES convergence on problems where RL learns well, but also helps RL training on other tasks, , fixes the injection issues better than previous controlled injection methods.