Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
mertyazan
/
Reinforce-1
like
0
Reinforcement Learning
Pixelcopter-PLE-v0
reinforce
custom-implementation
deep-rl-class
Eval Results
Model card
Files
Files and versions
Community
78f47d2
Reinforce-1
/
hyperparameters.json
mertyazan
Upload . with huggingface_hub
082df83
over 1 year ago
raw
Copy download link
history
blame
187 Bytes
{
"h_size"
:
96
,
"n_training_episodes"
:
30000
,
"n_evaluation_episodes"
:
10
,
"max_t"
:
10000
,
"gamma"
:
0.99
,
"lr"
:
0.0001
,
"env_id"
:
"Pixelcopter-PLE-v0"
,
"state_space"
:
7
,
"action_space"
:
2
}