Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
alexbalandi
/
ppo-LunarLander-v2-4milsteps-200-envs
like
0
Reinforcement Learning
stable-baselines3
LunarLander-v2
deep-reinforcement-learning
Eval Results
Model card
Files
Files and versions
Community
Use this model
3120398
ppo-LunarLander-v2-4milsteps-200-envs
/
FinetunedPPO_5mil_steps_total
1 contributor
History:
1 commit
alexbalandi
Upload PPO LunarLander-v2 trained agent, used 1 mil more steps with more loose variance hyperparameter.
3120398
almost 2 years ago
_stable_baselines3_version
Safe
5 Bytes
Upload PPO LunarLander-v2 trained agent, used 1 mil more steps with more loose variance hyperparameter.
almost 2 years ago
data
Safe
24.1 kB
Upload PPO LunarLander-v2 trained agent, used 1 mil more steps with more loose variance hyperparameter.
almost 2 years ago
policy.optimizer.pth
Safe
88.1 kB
LFS
Upload PPO LunarLander-v2 trained agent, used 1 mil more steps with more loose variance hyperparameter.
almost 2 years ago
policy.pth
Safe
43.4 kB
LFS
Upload PPO LunarLander-v2 trained agent, used 1 mil more steps with more loose variance hyperparameter.
almost 2 years ago
pytorch_variables.pth
Safe
pickle
Pickle imports
No problematic imports detected
What is a pickle import?
431 Bytes
LFS
Upload PPO LunarLander-v2 trained agent, used 1 mil more steps with more loose variance hyperparameter.
almost 2 years ago
system_info.txt
Safe
226 Bytes
Upload PPO LunarLander-v2 trained agent, used 1 mil more steps with more loose variance hyperparameter.
almost 2 years ago