dylwil3
/

ppo-LunarLander-v2

Reinforcement Learning

stable-baselines3

deep-reinforcement-learning

Eval Results (legacy)

Model card Files Files and versions

ppo-LunarLander-v2

1 contributor

History: 3 commits

dylwil3's picture

Attempt with KL cutoff, eval callback, and new hyperparams.

6c91cd8 almost 3 years ago

best_model
Attempt with KL cutoff, eval callback, and new hyperparams. almost 3 years ago
ppo-LunarLander-v2
First attempt at lunar lander. 1e6 time step training. almost 3 years ago
.gitattributes

1.48 kB

initial commit almost 3 years ago
README.md

784 Bytes

Attempt with KL cutoff, eval callback, and new hyperparams. almost 3 years ago
best_model.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
147 kB
xet

Attempt with KL cutoff, eval callback, and new hyperparams. almost 3 years ago
config.json

13.5 kB

Attempt with KL cutoff, eval callback, and new hyperparams. almost 3 years ago
ppo-LunarLander-v2.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
147 kB
xet

First attempt at lunar lander. 1e6 time step training. almost 3 years ago
replay.mp4

220 kB

Attempt with KL cutoff, eval callback, and new hyperparams. almost 3 years ago
results.json

164 Bytes

Attempt with KL cutoff, eval callback, and new hyperparams. almost 3 years ago