# MoE-Loco: Mixture of Experts for Multitask Locomotion

arXiv: https://arxiv.org/abs/2503.08564 · HTML: https://mlsanity.com/paper/2503.08564/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in MoE in reinforcement learning and robotics, one of 12 directions in Mixture-of-experts.
- Builds on 39 of its 54 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Placed in

- Mixture-of-experts / [MoE in reinforcement learning and robotics](https://mlsanity.com/moe/moe-in-reinforcement-learning-and-robotics/)

## Builds on (most cited first, 30 of 39)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [Learning agile and dynamic motor skills for legged robots](https://mlsanity.com/paper/1901.08652/) (2019)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Conflict-Averse Gradient Descent for Multi-task Learning](https://mlsanity.com/paper/2110.14048/) (2021)
- [Multi-Task Reinforcement Learning with Context-based Representations](https://mlsanity.com/paper/2102.06177/) (2021)
- [Rapid Locomotion via Reinforcement Learning](https://mlsanity.com/paper/2205.02824/) (2022)
- [Extreme Parkour with Legged Robots](https://mlsanity.com/paper/2309.14341/) (2023)
- [ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots](https://mlsanity.com/paper/2306.14874/) (2023)
- [Robot Parkour Learning](https://mlsanity.com/paper/2309.05665/) (2023)
- [Recurrent Neural Network for Text Classification with Multi-Task Learning](https://mlsanity.com/paper/1605.05101/) (2016)
- [Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning](https://mlsanity.com/paper/2312.12379/) (2023)
- [GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields](https://mlsanity.com/paper/2308.16891/) (2023)
- [Distributed Gaussian Processes](https://mlsanity.com/paper/1502.02843/) (2015)
- [LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMs](https://mlsanity.com/paper/2401.16160/) (2024)
- [Mixtures of Experts Unlock Parameter Scaling for Deep RL](https://mlsanity.com/paper/2402.08609/) (2024)
- [Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion](https://mlsanity.com/paper/2401.17583/) (2024)
- [Multi-expert learning of adaptive legged locomotion](https://mlsanity.com/paper/2012.05810/) (2020)
- [Learning Humanoid Locomotion with Perceptive Internal Model](https://mlsanity.com/paper/2411.14386/) (2024)
- [Learning to Push by Grasping: Using multiple tasks for effective learning](https://mlsanity.com/paper/1609.09025/) (2016)
- [M3oE: Multi-Domain Multi-Task Mixture-of Experts Recommendation Framework](https://mlsanity.com/paper/2404.18465/) (2024)
- [Leveraging Symmetry in RL-based Legged Locomotion Control](https://mlsanity.com/paper/2403.17320/) (2024)
- [PIE: Parkour with Implicit-Explicit Learning Framework for Legged Robots](https://mlsanity.com/paper/2408.13740/) (2024)
- [MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning](https://mlsanity.com/paper/2410.14972/) (2024)
- [ManyQuadrupeds: Learning a Single Locomotion Policy for Diverse Quadruped Robots](https://mlsanity.com/paper/2310.10486/) (2023)

## Built on by (most cited first, 23 of 23)

- [Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoids](https://mlsanity.com/paper/2601.07718/) (2026)
- [MoE-DP: An MoE-Enhanced Diffusion Policy for Robust Long-Horizon Robotic Manipulation with Skill Decomposition and Failure Recovery](https://mlsanity.com/paper/2511.05007/) (2025)
- [Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning](https://mlsanity.com/paper/2506.05985/) (2025)
- [Flexible Multitask Learning with Factorized Diffusion Policy](https://mlsanity.com/paper/2512.21898/) (2025)
- [MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free](https://mlsanity.com/paper/2601.02967/) (2026)
- [TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkour](https://mlsanity.com/paper/2602.02331/) (2026)
- [Generative Large-Scale Pre-trained Models for Automated Ad Bidding Optimization](https://mlsanity.com/paper/2508.02002/) (2025)
- [Toward Reliable Sim-to-Real Predictability for MoE-based Robust Quadrupedal Locomotion](https://mlsanity.com/paper/2602.00678/) (2026)
- [SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning](https://mlsanity.com/paper/2605.04712/) (2026)
- [SARM2: Multi-Task Stage Aware Reward Modeling for Self Improving Robotic Manipulation](https://mlsanity.com/paper/2606.10305/) (2026)
- [MoE-CE: Enhancing Generalization for Deep Learning based Channel Estimation via a Mixture-of-Experts Framework](https://mlsanity.com/paper/2509.15964/) (2025)
- [Flexible Locomotion Learning with Diffusion Model Predictive Control](https://mlsanity.com/paper/2510.04234/) (2025)
- [MoRI: Mixture of RL and IL Experts for Long-Horizon Manipulation Tasks](https://mlsanity.com/paper/2604.10165/) (2026)
- [LiMoDE: Rethinking Lifelong Robot Manipulation from a Mixture-of-Dynamic-Experts Perspective](https://mlsanity.com/paper/2606.26183/) (2026)
- [PPL: Point Cloud Supervised Proprioceptive Locomotion Reinforcement Learning for Legged Robots in Crawl Spaces](https://mlsanity.com/paper/2508.09950/) (2025)
- [KiRAS: Keyframe Guided Self-Imitation for Robust and Adaptive Skill Learning in Quadruped Robots](https://mlsanity.com/paper/2603.15179/) (2026)
- [Tree Learning: A Multi-Skill Continual Learning Framework for Humanoid Robots](https://mlsanity.com/paper/2604.12909/) (2026)
- [CoRe-MoE: Contrastive Reweighted Mixture of Experts for Multi-Terrain Humanoid Locomotion with Gait Adaptation](https://mlsanity.com/paper/2606.04718/) (2026)
- [Y-BotFrame: An Extensible Embodied Agent Framework for Quadruped Robot Assistants](https://mlsanity.com/paper/2606.13049/) (2026)
- [CTS-MoE: Implicit Terrain Adaptation via Mixture-of-Experts for Perceptive Locomotion](https://mlsanity.com/paper/2606.19633/) (2026)
- [CoRDE: Concept-Prior Routed Diffusion Experts for Structural Generalization in Robot Manipulation](https://mlsanity.com/paper/2606.21935/) (2026)
- [Self-Adaptive Learning and Model Predictive Control for Tracking Unknown Dynamics with No Regret](https://mlsanity.com/paper/2607.26370/) (2026)
- [Teaching a Robot Dog New Tricks: Diverse Quadruped Skills via Combined Reinforcement and Imitation Learning with Adversarial Task Selection](https://mlsanity.com/paper/2610.10601/) (2026)

## Abstract (arXiv)

We present MoE-Loco, a Mixture of Experts (MoE) framework for multitask locomotion for legged robots. Our method enables a single policy to handle diverse terrains, including bars, pits, stairs, slopes, and baffles, while supporting quadrupedal and bipedal gaits. Using MoE, we mitigate the gradient conflicts that typically arise in multitask reinforcement learning, improving both training efficiency and performance. Our experiments demonstrate that different experts naturally specialize in distinct locomotion behaviors, which can be leveraged for task migration and skill composition. We further validate our approach in both simulation and real-world deployment, showcasing its robustness and adaptability.