Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
auriolar
/
Reinforce-Pong-PLE-v0
like
0
Reinforcement Learning
Pong-PLE-v0
reinforce
custom-implementation
deep-rl-class
Eval Results
Model card
Files
Files and versions
Community
4e81aae
Reinforce-Pong-PLE-v0
/
hyperparameters.json
auriolar
Push Reinforce agent to the Hub
4e81aae
over 2 years ago
raw
Copy download link
history
blame
Safe
177 Bytes
{
"h_size"
:
64
,
"n_training_episodes"
:
20000
,
"n_evaluation_episodes"
:
10
,
"max_t"
:
5000
,
"gamma"
:
0.99
,
"lr"
:
0.01
,
"env_id"
:
"Pong-PLE-v0"
,
"state_space"
:
7
,
"action_space"
:
3
}