kyeongpil
/

Reinforce-CartPole-v1

Reinforcement Learning

CartPole-v1

reinforce

custom-implementation

deep-rl-class

Eval Results

Model card Files Files and versions Community

Reinforce-CartPole-v1 / hyperparameters.json

kyeongpil

Upload . with huggingface_hub

dc14eb6 about 2 years ago

raw

history blame

178 Bytes

{"h_size": 16, "n_training_episodes": 1000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 0.996, "lr": 0.005, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}