Harm
/

Reinforce-Pixelcopter-PLE-v0

Reinforcement Learning

Pixelcopter-PLE-v0

reinforce

custom-implementation

deep-rl-class

Eval Results (legacy)

Model card Files Files and versions

xet

Community

Reinforce-Pixelcopter-PLE-v0 / hyperparameters.json

Harm

Upload . with huggingface_hub

67ba630 almost 4 years ago

Raw History Blame Contribute Delete

185 Bytes

{"h_size": 64, "n_training_episodes": 20000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 0.95, "lr": 1e-05, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}