Q-Learning agent playing FrozenLake-v1
This is a trained model of an Q-Learning agent playing FrozenLake-v1 for the Hugging Face Deep Reinforcement Learning Course (Unit 2 (FrozenLake 4x4)).
Evaluation Results
- Mean Reward: 1.00 +/- 0.00
- Environment: FrozenLake-v1
- Algorithm: Q-Learning
- Library: q-learning
Usage
Trained and evaluated for the Hugging Face Deep RL Course.
Evaluation results
- mean_reward on FrozenLake-v1self-reported1.00 +/- 0.00