# Learning Fast Adaptation with Meta Strategy Optimization

arXiv: https://arxiv.org/abs/1909.12995 · HTML: https://mlsanity.com/paper/1909.12995/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2019.

## Built on by (most cited first, 30 of 48)

- [RMA: Rapid Motor Adaptation for Legged Robots](https://mlsanity.com/paper/2107.04034/) (2021)
- [How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned](https://mlsanity.com/paper/2102.02915/) (2021)
- [Extreme Parkour with Legged Robots](https://mlsanity.com/paper/2309.14341/) (2023)
- [Legged Locomotion in Challenging Terrains using Egocentric Vision](https://mlsanity.com/paper/2211.07638/) (2022)
- [Human-Timescale Adaptation in an Open-Ended Task Space](https://mlsanity.com/paper/2301.07608/) (2023)
- [ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills](https://mlsanity.com/paper/2502.01143/) (2025)
- [Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion](https://mlsanity.com/paper/2210.10044/) (2022)
- [Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots](https://mlsanity.com/paper/2103.14295/) (2021)
- [A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning](https://mlsanity.com/paper/2208.07860/) (2022)
- [Fast and Efficient Locomotion via Learned Gait Transitions](https://mlsanity.com/paper/2104.04644/) (2021)
- [Adapting Rapid Motor Adaptation for Bipedal Robots](https://mlsanity.com/paper/2205.15299/) (2022)
- [Coupling Vision and Proprioception for Navigation of Legged Robots](https://mlsanity.com/paper/2112.02094/) (2021)
- [Safe Reinforcement Learning for Legged Locomotion](https://mlsanity.com/paper/2203.02638/) (2022)
- [Learning and Adapting Agile Locomotion Skills by Transferring Experience](https://mlsanity.com/paper/2304.09834/) (2023)
- [From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robots](https://mlsanity.com/paper/2506.12779/) (2025)
- [Curious Replay for Model-based Adaptation](https://mlsanity.com/paper/2306.15934/) (2023)
- [Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Models](https://mlsanity.com/paper/2407.02666/) (2024)
- [Sim-to-Real Transfer for Quadrupedal Locomotion via Terrain Transformer](https://mlsanity.com/paper/2212.07740/) (2022)
- [PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations](https://mlsanity.com/paper/2207.13224/) (2022)
- [Cascaded Compositional Residual Learning for Complex Interactive Behaviors](https://mlsanity.com/paper/2212.08954/) (2022)
- [Towards a Pretrained Model for Restless Bandits via Multi-arm Generalization](https://mlsanity.com/paper/2310.14526/) (2023)
- [Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment](https://mlsanity.com/paper/2311.01059/) (2023)
- [Learning and Fast Adaptation for Grid Emergency Control via Deep Meta Reinforcement Learning](https://mlsanity.com/paper/2101.05317/) (2021)
- [ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI](https://mlsanity.com/paper/2410.02751/) (2024)
- [Robot Trains Robot: Automatic Real-World Policy Adaptation and Learning for Humanoids](https://mlsanity.com/paper/2508.12252/) (2025)
- [Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning](https://mlsanity.com/paper/2502.02332/) (2025)
- [Pay Attention to How You Drive: Safe and Adaptive Model-Based Reinforcement Learning for Off-Road Driving](https://mlsanity.com/paper/2310.08674/) (2023)
- [Discovering Adaptable Symbolic Algorithms from Scratch](https://mlsanity.com/paper/2307.16890/) (2023)
- [Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics](https://mlsanity.com/paper/2304.12289/) (2023)
- [BayRnTune: Adaptive Bayesian Domain Randomization via Strategic Fine-tuning](https://mlsanity.com/paper/2310.10606/) (2023)

## 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.