olokshyn
/

ppo-LunarLander-v2

Reinforcement Learning

stable-baselines3

deep-reinforcement-learning

Eval Results (legacy)

Model card Files Files and versions

ppo-LunarLander-v2

Ctrl+K

Ctrl+K

1 contributor

History: 4 commits

olokshyn's picture

Trained for 1,500,000 timesteps

98e3d5f verified over 1 year ago

ppo-LunarLander-v2-v3
1 million total steps, higher lr almost 4 years ago
ppo-LunarLander-v2
Trained for 1,500,000 timesteps over 1 year ago
.gitattributes

1.22 kB
Default parameters almost 4 years ago
README.md

784 Bytes
Trained for 1,500,000 timesteps over 1 year ago
config.json

13.7 kB
Trained for 1,500,000 timesteps over 1 year ago
ppo-LunarLander-v2-v3.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
145 kB
xet

1 million total steps, higher lr almost 4 years ago
ppo-LunarLander-v2.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
148 kB
xet

Trained for 1,500,000 timesteps over 1 year ago
replay.mp4

167 kB
xet

Trained for 1,500,000 timesteps over 1 year ago
results.json

157 Bytes
Trained for 1,500,000 timesteps over 1 year ago