# Robust Quadruped Locomotion via Evolutionary Reinforcement Learning

arXiv: https://arxiv.org/abs/2604.07224 · HTML: https://mlsanity.com/paper/2604.07224/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 10 of 10)

- [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)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [Exploration in Deep Reinforcement Learning: A Survey](https://mlsanity.com/paper/2205.00824/) (2022)
- [CEM-RL: Combining evolutionary and gradient-based methods for policy search](https://mlsanity.com/paper/1810.01222/) (2018)
- [Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning](https://mlsanity.com/paper/2003.01239/) (2020)
- [Evolutionary Reinforcement Learning: A Survey](https://mlsanity.com/paper/2303.04150/) (2023)
- [Reinforcement Learning with Evolutionary Trajectory Generator: A General Approach for Quadrupedal Locomotion](https://mlsanity.com/paper/2109.06409/) (2021)
- [Evolving Multi-Objective Neural Network Controllers for Robot Swarms](https://mlsanity.com/paper/2307.14237/) (2023)
- [Behavior evolution-inspired approach to walking gait reinforcement training for quadruped robots](https://mlsanity.com/paper/2409.16862/) (2024)

## Abstract (arXiv)

Deep reinforcement learning has recently achieved strong results in quadrupedal locomotion, yet policies trained in simulation often fail to transfer when the environment changes. Evolutionary reinforcement learning aims to address this limitation by combining gradient-based policy optimisation with population-driven exploration. This work evaluates four methods on a simulated walking task: DDPG, TD3, and two Cross-Entropy-based variants CEM-DDPG and CEM-TD3. All agents are trained on flat terrain and later tested both on this domain and on a rough terrain not encountered during training. TD3 performs best among the standard deep RL baselines on flat ground with a mean reward of 5927.26, while CEM-TD3 achieves the highest rewards overall during training and evaluation 17611.41. Under the rough-terrain transfer test, performance of the deep RL methods drops sharply. DDPG achieves -1016.32 and TD3 achieves -99.73, whereas the evolutionary variants retain much of their capability. CEM-TD3 records the strongest transfer performance with a mean reward of 19574.33. These findings suggest that incorporating evolutionary search can reduce overfitting and improve policy robustness in locomotion tasks, particularly when deployment conditions differ from those seen during training.