Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Oleg78
/
PixelCopter
like
0
Reinforcement Learning
Pixelcopter-PLE-v0
reinforce
custom-implementation
deep-rl-class
Eval Results
Model card
Files
Files and versions
Community
c32f2c9
PixelCopter
/
hyperparameters.json
Oleg78
Push Reinforce agent to the Hub
6fd1db9
almost 2 years ago
raw
Copy download link
history
blame
Safe
187 Bytes
{
"h_size"
:
64
,
"n_training_episodes"
:
50000
,
"n_evaluation_episodes"
:
10
,
"max_t"
:
10000
,
"gamma"
:
0.99
,
"lr"
:
0.0001
,
"env_id"
:
"Pixelcopter-PLE-v0"
,
"state_space"
:
7
,
"action_space"
:
2
}