wwymak
/

ppo-LunarLander-v2

Reinforcement Learning

stable-baselines3

deep-reinforcement-learning

Model card Files Files and versions Community

ppo-LunarLander-v2

1 contributor

History: 5 commits

wwymak's picture

lunar lander tuned, 1e6 timesteps, params: {'n_steps': 1024, 'n_epochs': 20, 'discount_factor_gamma': 0.999}

d5487bb over 2 years ago

lunar v1
lunar lander default training, 1e6 timesteps over 2 years ago
lunar v2
lunar lander tuned, 1e6 timesteps, params: {'n_steps': 1024, 'n_epochs': 20, 'discount_factor_gamma': 0.999} over 2 years ago
.gitattributes

1.22 kB

lunar lander default training, 1e6 timesteps over 2 years ago
README.md

677 Bytes

lunar lander tuned, 1e6 timesteps, params: {'n_steps': 1024, 'n_epochs': 20, 'discount_factor_gamma': 0.999} over 2 years ago
config.json

14.5 kB

lunar lander tuned, 1e6 timesteps, params: {'n_steps': 1024, 'n_epochs': 20, 'discount_factor_gamma': 0.999} over 2 years ago
lunar v1.zip

144 kB
LFS

lunar lander default training, 1e6 timesteps over 2 years ago
lunar v2.zip

144 kB
LFS

lunar lander tuned, 1e6 timesteps, params: {'n_steps': 1024, 'n_epochs': 20, 'discount_factor_gamma': 0.999} over 2 years ago
replay.mp4

202 kB
LFS

lunar lander tuned, 1e6 timesteps, params: {'n_steps': 1024, 'n_epochs': 20, 'discount_factor_gamma': 0.999} over 2 years ago
results.json

165 Bytes

lunar lander tuned, 1e6 timesteps, params: {'n_steps': 1024, 'n_epochs': 20, 'discount_factor_gamma': 0.999} over 2 years ago