Hugging Face's logo

nikitakapitan
/
FrozenLake-v2-4x4-Slippery

Reinforcement Learning
FrozenLake-v1-4x4
q-learning
custom-implementation
Eval Results
Model card Files Community
FrozenLake-v2-4x4-Slippery / results.json
nikitakapitan's picture
nikitakapitan
Push Q-Learning agent to Hub
c5c3224
raw
history blame contribute delete
121 Bytes
{"env_id": "FrozenLake-v1", "mean_reward": 0.726, "n_eval_episodes": 2000, "eval_datetime": "2022-08-04T14:36:17.633409"}