Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
fermaat
/
ppo-LunarLander-scratch
like
0
Reinforcement Learning
TensorBoard
LunarLander-v2
ppo
deep-reinforcement-learning
custom-implementation
deep-rl-course
Eval Results
Model card
Files
Files and versions
Metrics
Training metrics
Community
bf0fe59
ppo-LunarLander-scratch
/
results.json
fermaat
Push agent to the Hub
bf0fe59
over 1 year ago
raw
Copy download link
history
blame
Safe
174 Bytes
{
"env_id"
:
"LunarLander-v2"
,
"mean_reward"
:
-14.302093163783747
,
"std_reward"
:
118.44641372830634
,
"n_evaluation_episodes"
:
10
,
"eval_datetime"
:
"2023-02-23T18:54:50.076481"
}