Q-Learning FrozenLake-v1 4x4 noSlippery
This repository contains a Q-Learning agent trained on FrozenLake-v1.
Environment
- Environment: FrozenLake-v1
- Map: 4x4
- Slippery: False
- Algorithm: Q-Learning
Files
q-learning.pkl: trained Q-table and hyperparameters.results.json: evaluation results.replay.mp4: replay video generated from the trained Q-table.
Video episode reward
Episode reward in replay: 1
