mlsanityData to 7 Oct 2026

Data Efficient Reinforcement Learning for Legged Robots

arXiv 1907.03613 ↗First posted 8 Jul 2019cs.LG cs.AI cs.ROcited by 60

Not on the map. Why?

Abstract (arXiv)

We present a model-based framework for robot locomotion that achieves walking based on only 4.5 minutes (45,000 control steps) of data collected on a quadruped robot. To accurately model the robot's dynamics over a long horizon, we introduce a loss function that tracks the model's prediction over multiple timesteps. We adapt model predictive control to account for planning latency, which allows the learned model to be used for real time control. Additionally, to ensure safe exploration during model learning, we embed prior knowledge of leg trajectories into the action space. The resulting system achieves fast and robust locomotion. Unlike model-free methods, which optimize for a particular task, our planner can use the same learned dynamics for various tasks, simply by changing the reward function. To the best of our knowledge, our approach is more than an order of magnitude more sample efficient than current model-free methods.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 11; 2022: 13; 2023: 9; 2024: 10; 2025: 15; 2026: 1.

60 papers.

Sort:

By area:

  1. 2020MOReL : Model-Based Offline Reinforcement Learningcited by 582
  2. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 430
  3. 2022DayDreamer: World Models for Physical Robot Learningcited by 372
  4. 2021How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learnedcited by 201
  5. 2024SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learningcited by 113
  6. 2022A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learningcited by 76
  7. 2021Fast and Efficient Locomotion via Learned Gait Transitionscited by 50
  8. 2025Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Roboticscited by 47
  9. 2021GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Modelcited by 23
  10. 2023Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotioncited by 21
  11. 2025Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classificationcited by 19
  12. 2021Learning Modular Robot Control Policiescited by 18
38 more
  1. 2021Vision-Guided Quadrupedal Locomotion in the Wild with Multi-Modal Delay Randomizationcited by 18
  2. 2022A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learningcited by 15
  3. 2024Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Modelscited by 15
  4. 2025Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robotscited by 15
  5. 2024Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Modelscited by 14
  6. 2022Regret Lower Bounds for Learning Linear Quadratic Gaussian Systemscited by 11
  7. 2022Inferring Smooth Control: Monte Carlo Posterior Policy Iteration with Gaussian Processescited by 10
  8. 2024Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learningcited by 8
  9. 2023Bridging Active Exploration and Uncertainty-Aware Deployment Using Probabilistic Ensemble Neural Network Dynamicscited by 7
  10. 2022World Robot Challenge 2020 -- Partner Robot: A Data-Driven Approach for Room Tidying with Mobile Manipulatorcited by 5
  11. 2022A Simple Decentralized Cross-Entropy Methodcited by 5
  12. 2023Safe Navigation in Unstructured Environments by Minimizing Uncertainty in Control and Perceptioncited by 5
  13. 2026Deep Whole-body Parkourcited by 5
  14. 2022Cloud-Edge Training Architecture for Sim-to-Real Deep Reinforcement Learningcited by 4
  15. 2024Dexterous Legged Locomotion in Confined 3D Spaces with Reinforcement Learningcited by 4
  16. 2024Simulation-Aided Policy Tuning for Black-Box Robot Learningcited by 4
  17. 2022Neighborhood Mixup Experience Replay: Local Convex Interpolation for Improved Sample Efficiency in Continuous Control Taskscited by 3
  18. 2022Minimizing Human Assistance: Augmenting a Single Demonstration for Deep Reinforcement Learningcited by 3
  19. 2023Synaptic motor adaptation: A three-factor learning rule for adaptive robotic control in spiking neural networkscited by 3
  20. 2024AnyBipe: An End-to-End Framework for Training and Deploying Bipedal Robots Guided by Large Language Modelscited by 3
  21. 2024Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Samplingcited by 3
  22. 2025Symmetry-Guided Memory Augmentation for Efficient Locomotion Learningcited by 3
  23. 2025TAR: Teacher-Aligned Representations via Contrastive Learning for Quadrupedal Locomotioncited by 3
  24. 2021Quadruped Locomotion on Non-Rigid Terrain using Reinforcement Learningcited by 2
  25. 2021Aligning an optical interferometer with beam divergence control and continuous action spacecited by 2
  26. 2021Optimal Actor-Critic Policy with Optimized Training Datasetscited by 2
  27. 2023Quality-Diversity Optimisation on a Physical Robot Through Dynamics-Aware and Reset-Free Learningcited by 2
  28. 2023Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learningcited by 2
  29. 2023BayRnTune: Adaptive Bayesian Domain Randomization via Strategic Fine-tuningcited by 2
  30. 2024Reinforcement Learning Interventions on Boundedly Rational Human Agents in Frictionful Taskscited by 2
  31. 2025Learning to Walk With Less: A Dyna-Style Approach to Quadrupedal Locomotioncited by 2
  32. 2025Learning Soft Robotic Dynamics with Active Explorationcited by 2
  33. 2024Learning to enhance multi-legged robot on rugged landscapescited by 1
  34. 2025Learning Terrain-Specialized Policies for Adaptive Locomotion in Challenging Environmentscited by 1
  35. 2021Error-Aware Policy Learning: Zero-Shot Generalization in Partially Observable Dynamic Environmentscited by 0
  36. 2021PM-FSM: Policies Modulating Finite State Machine for Robust Quadrupedal Locomotioncited by 0
  37. 2022Learning Modular Robot Locomotion from Demonstrationscited by 0
  38. 2022Efficient Learning of Voltage Control Strategies via Model-based Deep Reinforcement Learningcited by 0

50 most cited of 60 All 60 (JSON)