Downloads · 30 days
8
7% of all-time downloads
heraGishtiTeamAiDatadominators26
ppo-LunarLander-v3
heraGishtiTeamAiDatadominators26/ppo-LunarLander-v3
ppo-LunarLander-v3 is a reinforcement learning model from heraGishtiTeamAiDatadominators26. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for stable-baselines3.
Trained with Stable-Baselines3 PPO for 1M timesteps as part of the Hugging Face Deep RL Course (Unit 8 — Proximal Policy Optimization).
All-time downloads
107
Public
Repo size
406 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.mp4212 KB · 52%
At a glance
- Task
- Reinforcement Learning
- Library
- stable-baselines3
- Access
- Public
- Created
- Apr 25, 2026
- Updated
- May 10, 2026
- SHA
- d9092cee
Model card
From the Hugging Face model README
PPO Agent playing LunarLander
Trained with Stable-Baselines3 PPO for 1M timesteps as part of the Hugging Face Deep RL Course (Unit 8 — Proximal Policy Optimization).
Note: trained on LunarLander-v3 from current Gymnasium (the v2 environment
is no longer registered). The dynamics and reward structure are identical
to v2; tags reflect the certification benchmark name.
Evaluation: mean reward = 271.21 +/- 17.91 over 10 episodes.
Training hyperparameters
- algorithm: PPO (MlpPolicy)
- n_envs: 16
- n_steps: 1024
- batch_size: 64
- n_epochs: 4
- gamma: 0.999
- gae_lambda: 0.98
- ent_coef: 0.01
- total_timesteps: 1_000_000
Usage
- Task
- Reinforcement Learning
- Library
- stable-baselines3
- Created
- Apr 25, 2026
- Updated
- May 10, 2026