mlsanityData to 14 Oct 2026

Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning

arXiv 2003.01239 ↗First posted 2 Mar 2020cs.RO cs.LG cs.NEcited by 43

Not on the map. Why?

Abstract (arXiv)

Learning adaptable policies is crucial for robots to operate autonomously in our complex and quickly changing world. In this work, we present a new meta-learning method that allows robots to quickly adapt to changes in dynamics. In contrast to gradient-based meta-learning algorithms that rely on second-order gradient estimation, we introduce a more noise-tolerant Batch Hill-Climbing adaptation operator and combine it with meta-learning based on evolutionary strategies. Our method significantly improves adaptation to changes in dynamics in high noise settings, which are common in robotics applications. We validate our approach on a quadruped robot that learns to walk while subject to changes in dynamics. We observe that our method significantly outperforms prior gradient-based approaches, enabling the robot to adapt its policy to changes based on less than 3 minutes of real data.

Key facts. Cited by 43 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 13; 2022: 11; 2023: 7; 2024: 4; 2025: 7; 2026: 1.

43 papers.

Sort:

By area:

  1. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 508
  2. 2022Legged Locomotion in Challenging Terrains using Egocentric Visioncited by 151
  3. 2023Robot Parkour Learningcited by 149
  4. 2022Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotioncited by 121
  5. 2022Neural-Fly Enables Rapid Learning for Agile Flight in Strong Windscited by 85
  6. 2022A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learningcited by 83
  7. 2021Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robotscited by 76
  8. 2021Fast and Efficient Locomotion via Learned Gait Transitionscited by 54
  9. 2022Adapting Rapid Motor Adaptation for Bipedal Robotscited by 54
  10. 2021Coupling Vision and Proprioception for Navigation of Legged Robotscited by 51
  11. 2021Lifelong Robotic Reinforcement Learning by Retaining Experiencescited by 34
  12. 2023Learning and Adapting Agile Locomotion Skills by Transferring Experiencecited by 33
31 more
  1. 2021Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Surveycited by 28
  2. 2025Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classificationcited by 26
  3. 2021Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platformscited by 22
  4. 2025LocoFormer: Generalist Locomotion via Long-context Adaptationcited by 20
  5. 2022Robust Policy Learning over Multiple Uncertainty Setscited by 18
  6. 2023Curious Replay for Model-based Adaptationcited by 16
  7. 2021On sensitivity of meta-learning to support datacited by 15
  8. 2022Sim-to-Real Transfer for Quadrupedal Locomotion via Terrain Transformercited by 14
  9. 2023Meta-Learning with a Geometry-Adaptive Preconditionercited by 11
  10. 2022PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representationscited by 10
  11. 2021MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerancecited by 8
  12. 2023Continuous Versatile Jumping Using Learned Action Residualscited by 8
  13. 2023Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deploymentcited by 8
  14. 2022Transfer Dynamics in Emergent Evolutionary Curriculacited by 6
  15. 2025Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learningcited by 6
  16. 2025Unsupervised Skill Discovery as Exploration for Learning Agile Locomotioncited by 6
  17. 2021Behavior Self-Organization Supports Task Inference for Continual Robot Learningcited by 4
  18. 2022Adaptive Prototypical Networkscited by 4
  19. 2024MPC of Uncertain Nonlinear Systems with Meta-Learning for Fast Adaptation of Neural Predictive Modelscited by 4
  20. 2023Moving Forward by Moving Backward: Embedding Action Impact over Action Semanticscited by 3
  21. 2025Meta-Learning Online Dynamics Model Adaptation in Off-Road Autonomous Drivingcited by 3
  22. 2024Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparatorcited by 2
  23. 2022A Survey on Deep Reinforcement Learning-based Approaches for Adaptation and Generalizationcited by 1
  24. 2024Impedance Matching: Enabling an RL-Based Running Jump in a Quadruped Robotcited by 1
  25. 2025CARoL: Context-aware Adaptation for Robot Learningcited by 1
  26. 2021ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spacescited by 0
  27. 2021Meta-Reinforcement Learning for Adaptive Motor Control in Changing Robot Dynamics and Environmentscited by 0
  28. 2021An Embarrassingly Pragmatic Introduction to Vision-based Autonomous Robotscited by 0
  29. 2024Perturbing the Gradient for Alleviating Meta Overfittingcited by 0
  30. 2025Beyond Fixed Morphologies: Learning Graph Policies with Trust Region Compensation in Variable Action Spacescited by 0
  31. 2026Robust Quadruped Locomotion via Evolutionary Reinforcement Learningcited by 0