bobobert4
/

ppo_lunar_lander-v2

Reinforcement Learning

stable-baselines3

deep-reinforcement-learning

Eval Results (legacy)

Model card Files Files and versions

ppo_lunar_lander-v2

1.06 MB

Ctrl+K

Ctrl+K

1 contributor

History: 4 commits

bobobert4's picture

More train steps

cb8e439 almost 3 years ago

lunar_landing_ppo_030723_01
1M learn steps almost 3 years ago
lunar_landing_ppo_030723_02
1M learn steps, learning_rate 5e-5, n_steps 800, ent_coef 5e-2 almost 3 years ago
ppo_lunar_lander-v2
More train steps almost 3 years ago
.gitattributes

1.52 kB
initial commit almost 3 years ago
README.md

802 Bytes
More train steps almost 3 years ago
config.json

13.6 kB
More train steps almost 3 years ago
lunar_landing_ppo_030723_01.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
147 kB
xet

1M learn steps almost 3 years ago
lunar_landing_ppo_030723_02.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
147 kB
xet

1M learn steps, learning_rate 5e-5, n_steps 800, ent_coef 5e-2 almost 3 years ago
ppo_lunar_lander-v2.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
147 kB
xet

More train steps almost 3 years ago
replay.mp4

166 kB
More train steps almost 3 years ago
results.json

156 Bytes
More train steps almost 3 years ago