maurorisonho

q-FrozenLake-v1-noSlippery

maurorisonho/q-FrozenLake-v1-noSlippery

q-FrozenLake-v1-noSlippery is a reinforcement learning model from maurorisonho. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product.

This model features a tuned Q-Learning Table with hyperparameters optimized via Optuna (Bayesian Search) on the deterministic FrozenLake-v1 (4x4) environment, demonstrating automated hyperparameter tuning for the Hugg…