Downloads · 30 days
0
unit8-ppo-lunarlander
MahaLakshmi2026/unit8-ppo-lunarlander
unit8-ppo-lunarlander is a reinforcement learning model from MahaLakshmi2026. 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 pytorch.
This repository contains a PPO (Proximal Policy Optimization) agent implemented from scratch using PyTorch for the Hugging Face Deep Reinforcement Learning Course Unit 8 Part I.
Access
Public
Updated Sep 23, 2026
Repo size
44.3 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt44.3 KB · 94%
At a glance
- Task
- Reinforcement Learning
- Library
- pytorch
- Access
- Public
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026
- SHA
- c5402d73
Model card
From the Hugging Face model README
PPO Agent playing LunarLander-v2
This repository contains a PPO (Proximal Policy Optimization) agent implemented from scratch using PyTorch for the Hugging Face Deep Reinforcement Learning Course Unit 8 Part I.
Training
- Algorithm: PPO
- Framework: PyTorch
- Environment: LunarLander-v3
- Certification environment tag: LunarLander-v2
- Training timesteps: 999,424
- Parallel environments: 16
- Device: CUDA
- Evaluation episodes: 10
Evaluation Results
- Mean Reward: -39.17
- Standard Deviation: 19.76
- Certification Score (mean - std): -58.93
The certification score is calculated as:
mean_reward - std_reward = -39.17 - 19.76 = -58.93
Files
ppo_lunarlander_v3.pt— trained PPO modelresults.json— evaluation results
- Task
- Reinforcement Learning
- Library
- pytorch
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026