Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
nondevs
/
Reinforce-Pixelcopter-PLE-v0
like
0
Reinforcement Learning
Pixelcopter-PLE-v0
reinforce
custom-implementation
deep-rl-class
Eval Results
Model card
Files
Files and versions
Community
68072af
Reinforce-Pixelcopter-PLE-v0
/
hyperparameters.txt
nondevs
Upload 4 files
68072af
about 1 year 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}