# Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning

arXiv: https://arxiv.org/abs/1803.11347 · HTML: https://mlsanity.com/paper/1803.11347/

## Key facts

- Cited by 276 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Mar 2018.

## Built on by (most cited first, 30 of 276)

- [RMA: Rapid Motor Adaptation for Legged Robots](https://mlsanity.com/paper/2107.04034/) (2021)
- [A Practical Guide to Multi-Objective Reinforcement Learning and Planning](https://mlsanity.com/paper/2103.09568/) (2021)
- [How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned](https://mlsanity.com/paper/2102.02915/) (2021)
- [A Survey of Zero-shot Generalisation in Deep Reinforcement Learning](https://mlsanity.com/paper/2111.09794/) (2021)
- [Legged Locomotion in Challenging Terrains using Egocentric Vision](https://mlsanity.com/paper/2211.07638/) (2022)
- [Robot Parkour Learning](https://mlsanity.com/paper/2309.05665/) (2023)
- [Supervised Pretraining Can Learn In-Context Reinforcement Learning](https://mlsanity.com/paper/2306.14892/) (2023)
- [Human-Timescale Adaptation in an Open-Ended Task Space](https://mlsanity.com/paper/2301.07608/) (2023)
- [Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents](https://mlsanity.com/paper/2402.11208/) (2024)
- [Rapid Exploration for Open-World Navigation with Latent Goal Models](https://mlsanity.com/paper/2104.05859/) (2021)
- [Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion](https://mlsanity.com/paper/2210.10044/) (2022)
- [Offline Meta-Reinforcement Learning with Advantage Weighting](https://mlsanity.com/paper/2008.06043/) (2020)
- [Few-Shot Preference Learning for Human-in-the-Loop RL](https://mlsanity.com/paper/2212.03363/) (2022)
- [Neural-Fly Enables Rapid Learning for Agile Flight in Strong Winds](https://mlsanity.com/paper/2205.06908/) (2022)
- [Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining](https://mlsanity.com/paper/2310.08566/) (2023)
- [DrEureka: Language Model Guided Sim-To-Real Transfer](https://mlsanity.com/paper/2406.01967/) (2024)
- [Continual Backprop: Stochastic Gradient Descent with Persistent Randomness](https://mlsanity.com/paper/2108.06325/) (2021)
- [MyoSuite -- A contact-rich simulation suite for musculoskeletal motor control](https://mlsanity.com/paper/2205.13600/) (2022)
- [A Survey on Model-based Reinforcement Learning](https://mlsanity.com/paper/2206.09328/) (2022)
- [Robot Learning from Randomized Simulations: A Review](https://mlsanity.com/paper/2111.00956/) (2021)
- [How Simulation Helps Autonomous Driving:A Survey of Sim2real, Digital Twins, and Parallel Intelligence](https://mlsanity.com/paper/2305.01263/) (2023)
- [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)
- [Generalizing to New Physical Systems via Context-Informed Dynamics Model](https://mlsanity.com/paper/2202.01889/) (2022)
- [AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning](https://mlsanity.com/paper/2107.02729/) (2021)
- [Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2110.13625/) (2021)
- [Maintaining Plasticity in Deep Continual Learning](https://mlsanity.com/paper/2306.13812/) (2023)
- [Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment](https://mlsanity.com/paper/2104.05632/) (2021)
- [PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning](https://mlsanity.com/paper/2106.04152/) (2021)
- [Adaptive-Control-Oriented Meta-Learning for Nonlinear Systems](https://mlsanity.com/paper/2103.04490/) (2021)

## Abstract (arXiv)

Although reinforcement learning methods can achieve impressive results in simulation, the real world presents two major challenges: generating samples is exceedingly expensive, and unexpected perturbations or unseen situations cause proficient but specialized policies to fail at test time. Given that it is impractical to train separate policies to accommodate all situations the agent may see in the real world, this work proposes to learn how to quickly and effectively adapt online to new tasks. To enable sample-efficient learning, we consider learning online adaptation in the context of model-based reinforcement learning. Our approach uses meta-learning to train a dynamics model prior such that, when combined with recent data, this prior can be rapidly adapted to the local context. Our experiments demonstrate online adaptation for continuous control tasks on both simulated and real-world agents. We first show simulated agents adapting their behavior online to novel terrains, crippled body parts, and highly-dynamic environments. We also illustrate the importance of incorporating online adaptation into autonomous agents that operate in the real world by applying our method to a real dynamic legged millirobot. We demonstrate the agent's learned ability to quickly adapt online to a missing leg, adjust to novel terrains and slopes, account for miscalibration or errors in pose estimation, and compensate for pulling payloads.