PPO LunarLander-v3
This model was trained as part of the Hugging Face Deep Reinforcement Learning Course — Unit 1.
Environment
LunarLander-v3
Algorithm
Proximal Policy Optimization (PPO)
Training
- Framework: Stable-Baselines3
- Timesteps: 1,000,000
- Parallel environments: 8
- Seed: 42
Evaluation
- Mean reward: 275.11
- Standard deviation: 19.77
- Mean minus standard deviation: 255.34
Important
This model uses the current Gymnasium environment:
LunarLander-v3
The older LunarLander-v2 environment is deprecated in current Gymnasium versions.
- Downloads last month
- 9