ppo-LunarLander-v3 is an open-weight model from Kevin Xu. Its published files total 383.2 KB.
video demo: https://huggingface.co/KevinLXu/ppo-LunarLander-v3/resolve/main/trained-lunarlander-step-0-to-step-1000.mp4 This is a trained model of a PPO agent playing LunarLander-v3 using the stable-baselines3 library.
Model Card
video demo: https://huggingface.co/KevinLXu/ppo-LunarLander-v3/resolve/main/trained-lunarlander-step-0-to-step-1000.mp4 This is a trained model of a PPO agent playing LunarLander-v3 using the stable-baselines3 library. https://huggingface.co/learn/deep-rl-course/unit1/hands-on
Excerpt from the card by Kevin Xu.
Identity and Version
- Repository
- KevinLXu/ppo-LunarLander-v3
- Publisher
- Kevin Xu
- Task
- Not stated by the source
- Modality
- Other
- Library
- stable-baselines3
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 19a658dfa92f48e323ce809a1acf46c17d9ad627
- First published
- 2026-10-03
- Last updated
- 2026-10-04
Files and Weights
12 files, 383.2 KB in total. The weights are 3 files totalling 134.1 KB in pth.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| ppo-LunarLander-v3/policy.optimizer.pth | Weights | 88.7 KB | b7be4f3d06a2 |
| ppo-LunarLander-v3/policy.pth | Weights | 44.1 KB | fdb1a06deaea |
| ppo-LunarLander-v3/pytorch_variables.pth | Weights | 1.3 KB | 07c7431cf600 |
| config.json | Configuration | 14.5 KB | — |
| results.json | Configuration | 164 B | — |
| README.md | Documentation | 937 B | — |
| ppo-LunarLander-v3.zip | Other | 150.4 KB | 102afaf025f9 |
| ppo-LunarLander-v3/_stable_baselines3_version | Other | 5 B | — |
| ppo-LunarLander-v3/data | Other | 15.3 KB | — |
| ppo-LunarLander-v3/system_info.txt | Other | 245 B | — |
| trained-lunarlander-step-0-to-step-1000.mp4 | Other | 66.2 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 134.1 KB
Released by Kevin Xu through its official repository on Hugging Face.
Evaluations
Each result is shown as reported, with the conditions its reporter stated. None is a SAVRN measurement. A comparison lines two results up only when their configuration, unit and setup are all stated and identical.
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| LunarLander-v3 | Task reinforcement-learningMetric mean_rewardComparison conditions not established | 242.63 +/- 21.53 | KevinLXu Publisher reported |
Evaluated revision not stated | — |
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 134.1 KB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.