unfinity
/

Reinforce-FrozenLake-v1

Reinforcement Learning

FrozenLake-v1-8x8-no_slippery

custom-implementation

Model card Files Files and versions Community

Reinforce-FrozenLake-v1 / hyperparameters.json

unfinity's picture

Push Reinforce agent to the Hub

2a9db5a over 2 years ago

126 Bytes

{"n_training_episodes": 1000, "n_evaluation_episodes": 100, "max_t": 200, "gamma": 1.0, "lr": 0.01, "env_id": "FrozenLake-v1"}