mlsanityData to 7 Oct 2026

DrEureka: Language Model Guided Sim-To-Real Transfer

arXiv 2406.01967 ↗First posted 4 Jun 2024cs.RO cs.AI cs.LGcited by 78

Not on the map. Why?

Abstract (arXiv)

Transferring policies learned in simulation to the real world is a promising strategy for acquiring robot skills at scale. However, sim-to-real approaches typically rely on manual design and tuning of the task reward function as well as the simulation physics parameters, rendering the process slow and human-labor intensive. In this paper, we investigate using Large Language Models (LLMs) to automate and accelerate sim-to-real design. Our LLM-guided sim-to-real approach, DrEureka, requires only the physics simulation for the target task and automatically constructs suitable reward functions and domain randomization distributions to support real-world transfer. We first demonstrate that our approach can discover sim-to-real configurations that are competitive with existing human-designed ones on quadruped locomotion and dexterous manipulation tasks. Then, we showcase that our approach is capable of solving novel robot tasks, such as quadruped balancing and walking atop a yoga ball, without iterative manual design.

Key facts. Cited by 78 papers in the map (data through 7 Oct 2026). Builds on 56 of its 73 references that are in the map. First posted on arXiv 4 Jun 2024.

Builds on

56 of 73 references.

References · 56

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  4. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  5. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  6. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  7. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  8. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  9. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  10. 2023Large Language Models as Optimizerscited by 830
  11. 2019Solving Rubik's Cube with a Robot Handcited by 699
  12. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 616
38 more
  1. 2022ProgPrompt: Generating Situated Robot Task Plans using Large Language Modelscited by 598
  2. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 542
  3. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
  4. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 494
  5. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 430
  6. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 395
  7. 2023Language to Rewards for Robotic Skill Synthesiscited by 307
  8. 2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robotscited by 277
  9. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 270
  10. 2023Text2Motion: From Natural Language Instructions to Feasible Planscited by 223
  11. 2023RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulationcited by 206
  12. 2018Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experiencecited by 203
  13. 2018Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networkscited by 171
  14. 2019Active Domain Randomizationcited by 161
  15. 2023Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisitioncited by 156
  16. 2023Task and Motion Planning with Large Language Models for Object Rearrangementcited by 140
  17. 2023Generalized Planning in PDDL Domains with Pretrained Large Language Modelscited by 139
  18. 2017Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Graspingcited by 138
  19. 2022DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Realitycited by 136
  20. 2023Translating Natural Language to Planning Goals with Large-Language Modelscited by 132
  21. 2022Rapid Locomotion via Reinforcement Learningcited by 130
  22. 2017Preparing for the Unknown: Learning a Universal Policy with Online System Identificationcited by 129
  23. 2023GenSim: Generating Robotic Simulation Tasks via Large Language Modelscited by 120
  24. 2023Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Modelcited by 115
  25. 2022Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behaviorcited by 113
  26. 2022In-Hand Object Rotation via Rapid Motor Adaptationcited by 102
  27. 2023Large Language Models as Generalizable Policies for Embodied Taskscited by 86
  28. 2023Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidancecited by 85
  29. 2019BayesSim: adaptive domain randomization via probabilistic inference for robotics simulatorscited by 78
  30. 2023LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learningcited by 78
  31. 2023Using Large Language Models for Hyperparameter Optimizationcited by 71
  32. 2023Language Models as Zero-Shot Trajectory Generatorscited by 59
  33. 2021Robot Learning from Randomized Simulations: A Reviewcited by 56
  34. 2020Dynamics Randomization Revisited:A Case Study for Quadrupedal Locomotioncited by 54
  35. 2023NEWTON: Are Large Language Models Capable of Physical Reasoning?cited by 45
  36. 2020Data-efficient Domain Randomization with Bayesian Optimizationcited by 43
  37. 2023SayTap: Language to Quadrupedal Locomotioncited by 40
  38. 2023Demo2Code: From Summarizing Demonstrations to Synthesizing Code via Extended Chain-of-Thoughtcited by 39

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 17; 2025: 24; 2026: 37.

78 papers.

Sort:

By area:

  1. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successescited by 153
  2. 2026CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulationcited by 72
  3. 2026ASPIRE: Agentic /Skills Discovery for Roboticscited by 44
  4. 2024Robot Utility Models: General Policies for Zero-Shot Deployment in New Environmentscited by 43
  5. 2024From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessonscited by 42
  6. 2026ENPIRE: Agentic Robot Policy Self-Improvement in the Real Worldcited by 31
  7. 2025Safety Guardrails for LLM-Enabled Robotscited by 30
  8. 2024CurricuLLM: Automatic Task Curricula Design for Learning Complex Robot Skills using Large Language Modelscited by 19
  9. 2026RHO: Your Coding Agent is Secretly a Roboticistcited by 18
  10. 2026Playful Agentic Robot Learningcited by 18
  11. 2024SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environmentscited by 16
  12. 2025A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AIcited by 16
38 more
  1. 2025ORV: 4D Occupancy-centric Robot Video Generationcited by 16
  2. 2024Eurekaverse: Environment Curriculum Generation via Large Language Modelscited by 14
  3. 2025Evolution and The Knightian Blindspot of Machine Learningcited by 11
  4. 2025Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environmentscited by 11
  5. 2025Air-Ground Collaboration for Language-Specified Missions in Unknown Environmentscited by 11
  6. 2024SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experiencecited by 10
  7. 2024Balancing Act: Prioritization Strategies for LLM-Designed Restless Bandit Rewardscited by 9
  8. 2024FactorSim: Generative Simulation via Factorized Representationcited by 9
  9. 2025GROVE: A Generalized Reward for Learning Open-Vocabulary Physical Skillcited by 9
  10. 2024RoboMorph: Evolving Robot Morphology using Large Language Modelscited by 8
  11. 2024Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Modelscited by 8
  12. 2025Maestro: Orchestrating Robotics Modules with Vision-Language Models for Zero-Shot Generalist Robotscited by 8
  13. 2024Generative AI Agents in Autonomous Machines: A Safety Perspectivecited by 7
  14. 2024ICPL: Few-shot In-context Preference Learning via LLMscited by 7
  15. 2026Act-Observe-Rewrite: Multimodal Coding Agents as In-Context Policy Learners for Robot Manipulationcited by 7
  16. 2024The Duality of Generative AI and Reinforcement Learning in Robotics: A Reviewcited by 5
  17. 2024Jailbreaking LLM-Controlled Robotscited by 4
  18. 2025LearningFlow: Automated Policy Learning Workflow for Urban Driving with Large Language Modelscited by 4
  19. 2025Al-Khwarizmi: Discovering Physical Laws with Foundation Modelscited by 4
  20. 2025A Real-to-Sim-to-Real Approach to Robotic Manipulation with VLM-Generated Iterative Keypoint Rewardscited by 4
  21. 2026From Generative Engines to Actionable Simulators: The Imperative of Physical Grounding in World Modelscited by 4
  22. 2026Lucid-XR: An Extended-Reality Data Engine for Robotic Manipulationcited by 4
  23. 2024AnyBipe: An End-to-End Framework for Training and Deploying Bipedal Robots Guided by Large Language Modelscited by 3
  24. 2024Language-Model-Assisted Bi-Level Programming for Reward Learning from Internet Videoscited by 3
  25. 2025Boosting Universal LLM Reward Design through Heuristic Reward Observation Space Evolutioncited by 2
  26. 2025PRISM: Projection-based Reward Integration for Scene-Aware Real-to-Sim-to-Real Transfer with Few Demonstrationscited by 2
  27. 2026Agentic Self-Evolutionary Replanning for Embodied Navigationcited by 2
  28. 2026HARBOR: A Harness Framework for Agentic Robot Reinforcement Learningcited by 2
  29. 2025Towards Autonomous Reinforcement Learning for Real-World Robotic Manipulation with Large Language Modelscited by 1
  30. 2025Neural Fidelity Calibration for Informative Sim-to-Real Adaptationcited by 1
  31. 2025AURA: Autonomous Upskilling with Retrieval-Augmented Agentscited by 1
  32. 2025Uncertainty-aware Reward Design Processcited by 1
  33. 2025Mitigating Goal Misgeneralization via Minimax Regretcited by 1
  34. 2025Mixed-Initiative Dialog for Human-Robot Collaborative Manipulationcited by 1
  35. 2025Text2Touch: Tactile In-Hand Manipulation with LLM-Designed Reward Functionscited by 1
  36. 2025On Discovering Algorithms for Adversarial Imitation Learningcited by 1
  37. 2026DCoPilot: Generative AI-Empowered Policy Adaptation for Dynamic Data Center Operationscited by 1
  38. 2026CoEnv: Driving Embodied Multi-Agent Collaboration via Compositional Environmentcited by 1

50 most cited of 78 All 78 (JSON)