Data to 7 Oct 2026

Meta Reinforcement Learning for Sim-to-real Domain Adaptation

arXiv 1909.12906 ↗First posted 16 Sep 2019cs.CV cs.ROcited by 49

Not on the map. Why?

Abstract (arXiv)

Modern reinforcement learning methods suffer from low sample efficiency and unsafe exploration, making it infeasible to train robotic policies entirely on real hardware. In this work, we propose to address the problem of sim-to-real domain transfer by using meta learning to train a policy that can adapt to a variety of dynamic conditions, and using a task-specific trajectory generation model to provide an action space that facilitates quick exploration. We evaluate the method by performing domain adaptation in simulation and analyzing the structure of the latent space during adaptation. We then deploy this policy on a KUKA LBR 4+ robot and evaluate its performance on a task of hitting a hockey puck to a target. Our method shows more consistent and stable domain adaptation than the baseline, resulting in better overall performance.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 12; 2023: 8; 2024: 12; 2025: 9; 2026: 1.

49 papers.

Sort:

By area:

2024Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Datacited by 58
2021Lifelong Robotic Reinforcement Learning by Retaining Experiencescited by 34
2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 32
2023An In-depth Survey of Large Language Model-based Artificial Intelligence Agentscited by 30
2024Multi-Agent Reinforcement Learning for Autonomous Driving: A Surveycited by 30
2024Cross-Domain Policy Adaptation by Capturing Representation Mismatchcited by 24
2021Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Surveycited by 23
2021Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platformscited by 22
2025The Reality Gap in Robotics: Challenges, Solutions, and Best Practicescited by 22
2022DROPO: Sim-to-Real Transfer with Offline Domain Randomizationcited by 16
2023Sim2real Transfer Learning for Point Cloud Segmentation: An Industrial Application Case on Autonomous Disassemblycited by 16
2022Latent-Variable Advantage-Weighted Policy Optimization for Offline RLcited by 12

37 more

2022SafeAPT: Safe Simulation-to-Real Robot Learning using Diverse Policies Learned in Simulationcited by 10
2024Effective Tuning Strategies for Generalist Robot Manipulation Policiescited by 10
2021MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerancecited by 7
2022Massively Digitized Power Grid: Opportunities and Challenges of Use-inspired AIcited by 6
2022Giving Feedback on Interactive Student Programs with Meta-Explorationcited by 6
2021Solving the Real Robot Challenge using Deep Reinforcement Learningcited by 5
2022Dexterous Robotic Manipulation using Deep Reinforcement Learning and Knowledge Transfer for Complex Sparse Reward-based Taskscited by 5
2023Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challengescited by 5
2025Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learningcited by 5
2024OMPO: A Unified Framework for RL under Policy and Dynamics Shiftscited by 4
2024Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolutioncited by 4
2025A Real-to-Sim-to-Real Approach to Robotic Manipulation with VLM-Generated Iterative Keypoint Rewardscited by 4
2022Coach-assisted Multi-Agent Reinforcement Learning Framework for Unexpected Crashed Agentscited by 3
2023A Conservative Approach for Few-Shot Transfer in Off-Dynamics Reinforcement Learningcited by 3
2024Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Reviewcited by 3
2023Bridging the Reality Gap of Reinforcement Learning based Traffic Signal Control using Domain Randomization and Meta Learningcited by 2
2023Robust Navigation with Cross-Modal Fusion and Knowledge Transfercited by 2
2024Data-Driven Simulator for Mechanical Circulatory Support with Domain Adversarial Neural Processcited by 2
2024Sim-to-Real Transfer of Deep Reinforcement Learning Agents for Online Coverage Path Planningcited by 2
2024Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparatorcited by 2
2025From Abstraction to Reality: DARPA's Vision for Robust Sim-to-Real Autonomycited by 2
2021Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptationcited by 1
2021Zero-Shot Uncertainty-Aware Deployment of Simulation Trained Policies on Real-World Robotscited by 1
2022A Survey on Deep Reinforcement Learning-based Approaches for Adaptation and Generalizationcited by 1
2022Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Modelscited by 1
2022Variational Meta Reinforcement Learning for Social Roboticscited by 1
2023Deep incremental learning models for financial temporal tabular datasets with distribution shiftscited by 1
2025Learning more with the same effort: how randomization improves the robustness of a robotic deep reinforcement learning agentcited by 1
2025A Multi-Fidelity Control Variate Approach for Policy Gradient Estimationcited by 1
2025The Emergence of Deep Reinforcement Learning for Path Planningcited by 1
2026Physics-Informed Eikonal Caging for Whole-Arm Manipulation Planningcited by 1
2022Domain Adapting Deep Reinforcement Learning for Real-world Speech Emotion Recognitioncited by 0
2023Bird's Eye View Based Pretrained World model for Visual Navigationcited by 0
2024Control-Theoretic Techniques for Online Adaptation of Deep Neural Networks in Dynamical Systemscited by 0
2024Benchmarks for Reinforcement Learning with Biased Offline Data and Imperfect Simulatorscited by 0
2025Dual Alignment Maximin Optimization for Offline Model-based RLcited by 0
2025Statistical Guarantees for Offline Domain Randomizationcited by 0