DeepTerrainRLxbpeng/DeepTerrainRL
Provides a deep reinforcement learning training codebase for terrain-adaptive locomotion control of quadruped robots,…
No ratings yet
Rate this skill
Stars463
Forks130
Watchers463
Open Issues17
InstallOne-line install
UnconfirmedWhether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:
git clone https://github.com/xbpeng/DeepTerrainRL.git
OverviewOverview
Key Features
Provides a deep reinforcement learning training codebase for terrain-adaptive locomotion control of quadruped robots, enabling researchers to train and reproduce walking policies over complex terrain in simulation. Key capabilities include: 1. Terrain-adaptive policy training: builds undulating, sloped, and stepped terrains in simulation and trains the robot with deep reinforcement learning to adjust gait and footholds in real time according to terrain, reducing manual tuning of hand-designed controllers; 2. Locomotion control experiment reproduction: offers a runnable training and evaluation pipeline that supports reproducing terrain-adaptive walking experiments from the paper, making it easy to compare algorithms and parameter settings; 3. Simulation environment interaction interface: wraps state observation, action execution, and reward computation between the robot and the simulator, so terrains, robot models, or reward functions can be swapped for new experiments.
Use Cases
Quadruped robot locomotion policy training on complex terrain, motion control algorithm research in simulation, deep reinforcement learning paper reproduction and experiment comparison, terrain-adaptive gait generation.
Target Roles
AI / Algorithm Engineer, Hardware / Embedded Engineer.
RatingUser ratings
Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.
RepositoryRepository
| Skill ID | 1886 |
|---|---|
| Data source | GitHub |
| Repository | xbpeng/DeepTerrainRL |
| Category | AI & Machine Learning / Reinforcement Learning & Robot Control |
| Primary language | C++ |
| License | GNU Lesser General Public License v3.0 |
| Default branch | master |
| GitHub repository ID | 55195086 |
| Node ID | MDEwOlJlcG9zaXRvcnk1NTE5NTA4Ng== |
| Rank | #1356 (position within the source ranking) |
| Site-wide popularity rank | #1538 (computed live from Stars, across all 5833 entries) |
GrowthStar / Fork growth
One snapshot per day, tracking how Stars and Forks changed
- Now463
- Previous point · 09-25 462
- vs previous point +1
- 2 data points 16 days
- Now130
- Previous point · 09-25 130
- vs previous point ±0
- 2 data points 16 days
TimelineTimeline
Repository created2016-04-01 01:39:092016-04-01
Data last updated2026-10-26 12:12:5921 days ago
Last commit2018-09-05 08:39:272018-09-05
CommitLatest commit
Version [Windows Build] committed by Neo-X. Update Category: Documentation & Guidelines Update. Commit details: Update README.md. This update improves usage instructions, deployment guides, and developer docs.