pith. sign in

arxiv: 1803.11347 · v6 · pith:LKHE6HWRnew · submitted 2018-03-30 · 💻 cs.LG · cs.RO· stat.ML

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

classification 💻 cs.LG cs.ROstat.ML
keywords learningonlinerealadaptadaptationagentsworldagent
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Solving Rubik's Cube with a Robot Hand

    cs.LG 2019-10 accept novelty 7.0

    Reinforcement learning models trained only in simulation using automatic domain randomization solve Rubik's cube with a real robot hand.

  2. Zero-Shot Sim-to-Real Robot Learning: A Dexterous Manipulation Study on Reactive Catching

    cs.RO 2026-05 unverdicted novelty 6.0

    DRIS improves zero-shot sim-to-real transfer for reactive catching by maintaining and acting on sets of randomized dynamics instances instead of single instances per episode.

  3. RoboNet: Large-Scale Multi-Robot Learning

    cs.RO 2019-10 conditional novelty 6.0

    RoboNet is a multi-robot video dataset that enables pre-training of vision-based manipulation models which, after fine-tuning on a new robot, outperform robot-specific training that uses 4-20 times more data.

  4. Environment Probing Interaction Policies

    cs.RO 2019-07 unverdicted novelty 6.0

    EPI policies use a transition-predictability reward to probe environments and condition task policies, outperforming standard generalization methods on novel test environments.

  5. An Information-Theoretic Analysis of OOD Generalization in Meta-Reinforcement Learning

    cs.LG 2025-10 unverdicted novelty 5.0

    The work establishes OOD generalization bounds for meta-supervised learning and meta-RL that exploit MDP structure, then analyzes a gradient-based meta-RL algorithm.