awesome-rl-for-legged-locomotion
github.com/apexrl/awesome-rl-for-legged-locomotion ↗A curated list of awesome material on legged robot locomotion using reinforcement learning (RL) and sim-to-real techniques.
185
GitHub Stars
33
Curated Resources
6
Categories
3 hours ago
Last Refreshed
Survey and ReviewsCore Papers by ETH Robotics System LabCore Papers by KAISTQuadruped LocomotionQuadruped Whole-Body ControlHumanoid Locomotion / Whole-Body Control / Loco-Manipulation
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me core papers by eth robotics system lab resources from awesome-rl-for-legged-locomotion"
Installation instructions →What's inside
Core Papers by ETH Robotics System Lab
- Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learning
- ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots
- Curiosity-Driven Learning of Joint Locomotion and Manipulation Tasks
- DTC: Deep Tracking Control
- Elevation Mapping for Locomotion and Navigation using GPU
- Learning Agile and Dynamic Motor Skills for Legged Robots
Quadruped Locomotion
- Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions
- Extreme Parkour with Legged Robots & Robot Parkour Learning
- Learning Agile Robotic Locomotion Skills by Imitating Animals
- Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations
- Learning Robust and Agile Legged Locomotion Using Adversarial Motion Priors
- Lifelike Agility and Play on Quadrupedal Robots Using Reinforcement Learning and Generative Pre-trained Models
Core Papers by KAIST
- A Learning Framework for Diverse Legged Robot Locomotion Using Barrier-Based Style Rewards
- Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotion
- DreamWaQ: Learning Robust Quadrupedal Locomotion with Implicit Terrain Imagination via Deep RL
- Learning Quadrupedal Locomotion on Deformable Terrain
Quadruped Whole-Body Control
Humanoid Locomotion / Whole-Body Control / Loco-Manipulation
- Expressive Whole-Body Control for Humanoid Robots
- HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots
- HugWBC: A Unified and General Humanoid Whole-Body Controller for Fine-Grained Locomotion
- Open-TeleVision: Teleoperation with Immersive Active Visual Feedback
- Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Composition
Showing a sample of 33 resources. View the full list on GitHub →