mlsanityData to 7 Oct 2026

Learning Fast Adaptation with Meta Strategy Optimization

arXiv 1909.12995 ↗First posted 28 Sep 2019cs.RO cs.LGcited by 46

Not on the map. Why?

Abstract (arXiv)

The ability to walk in new scenarios is a key milestone on the path toward real-world applications of legged robots. In this work, we introduce Meta Strategy Optimization, a meta-learning algorithm for training policies with latent variable inputs that can quickly adapt to new scenarios with a handful of trials in the target environment. The key idea behind MSO is to expose the same adaptation process, Strategy Optimization (SO), to both the training and testing phases. This allows MSO to effectively learn locomotion skills as well as a latent space that is suitable for fast adaptation. We evaluate our method on a real quadruped robot and demonstrate successful adaptation in various scenarios, including sim-to-real transfer, walking with a weakened motor, or climbing up a slope. Furthermore, we quantitatively analyze the generalization capability of the trained policy in simulated environments. Both real and simulated experiments show that our method outperforms previous methods in adaptation to novel tasks.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 9; 2023: 13; 2024: 5; 2025: 9; 2026: 1.

46 papers.

Sort:

By area:

  1. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 430
  2. 2021How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learnedcited by 201
  3. 2023Human-Timescale Adaptation in an Open-Ended Task Spacecited by 136
  4. 2022Legged Locomotion in Challenging Terrains using Egocentric Visioncited by 131
  5. 2023Extreme Parkour with Legged Robotscited by 120
  6. 2025ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skillscited by 104
  7. 2022Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotioncited by 98
  8. 2021Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robotscited by 95
  9. 2022A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learningcited by 76
  10. 2021Fast and Efficient Locomotion via Learned Gait Transitionscited by 50
  11. 2021Coupling Vision and Proprioception for Navigation of Legged Robotscited by 46
  12. 2022Adapting Rapid Motor Adaptation for Bipedal Robotscited by 39
34 more
  1. 2022Safe Reinforcement Learning for Legged Locomotioncited by 29
  2. 2023Learning and Adapting Agile Locomotion Skills by Transferring Experiencecited by 25
  3. 2023Curious Replay for Model-based Adaptationcited by 16
  4. 2025From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robotscited by 16
  5. 2024Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Modelscited by 15
  6. 2022Sim-to-Real Transfer for Quadrupedal Locomotion via Terrain Transformercited by 12
  7. 2022PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representationscited by 10
  8. 2022Cascaded Compositional Residual Learning for Complex Interactive Behaviorscited by 9
  9. 2023Towards a Pretrained Model for Restless Bandits via Multi-arm Generalizationcited by 9
  10. 2023Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deploymentcited by 7
  11. 2021Learning and Fast Adaptation for Grid Emergency Control via Deep Meta Reinforcement Learningcited by 6
  12. 2025Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learningcited by 5
  13. 2023Discovering Adaptable Symbolic Algorithms from Scratchcited by 4
  14. 2023Pay Attention to How You Drive: Safe and Adaptive Model-Based Reinforcement Learning for Off-Road Drivingcited by 4
  15. 2023Moving Forward by Moving Backward: Embedding Action Impact over Action Semanticscited by 3
  16. 2023A Conservative Approach for Few-Shot Transfer in Off-Dynamics Reinforcement Learningcited by 3
  17. 2024ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AIcited by 3
  18. 2025PrivilegedDreamer: Explicit Imagination of Privileged Information for Rapid Adaptation of Learned Policiescited by 3
  19. 2025Meta-Learning Online Dynamics Model Adaptation in Off-Road Autonomous Drivingcited by 3
  20. 2021Physics-informed Evolutionary Strategy based Control for Mitigating Delayed Voltage Recoverycited by 2
  21. 2023ECoDe: A Sample-Efficient Method for Co-Design of Robotic Agentscited by 2
  22. 2023BayRnTune: Adaptive Bayesian Domain Randomization via Strategic Fine-tuningcited by 2
  23. 2024Combining Federated Learning and Control: A Surveycited by 2
  24. 2025PolySim: Bridging the Sim-to-Real Gap for Humanoid Control via Multi-Simulator Dynamics Randomizationcited by 2
  25. 2025Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learningcited by 2
  26. 2022Fast Model-based Policy Search for Universal Policy Networkscited by 1
  27. 2025Hierarchical Reinforcement Learning and Value Optimization for Challenging Quadruped Locomotioncited by 1
  28. 2021Error-Aware Policy Learning: Zero-Shot Generalization in Partially Observable Dynamic Environmentscited by 0
  29. 2021PM-FSM: Policies Modulating Finite State Machine for Robust Quadrupedal Locomotioncited by 0
  30. 2023Learning Visual Tracking and Reaching with Deep Reinforcement Learning on a UR10e Robotic Armcited by 0
  31. 2024Stochastic Dynamic Power Dispatch with High Generalization and Few-Shot Adaption via Contextual Meta Graph Reinforcement Learningcited by 0
  32. 2024Impedance Matching: Enabling an RL-Based Running Jump in a Quadruped Robotcited by 0
  33. 2025Adaptive MPC-based quadrupedal robot control under periodic disturbancescited by 0
  34. 2026HERO: Learning Humanoid End-Effector Control for Visual Whole-Body Open-Vocabulary Object Graspingcited by 0