/Frozen-lake-Gym-Game

A game environment facilitated by GYM. Solved using RL to an average reward of 0.7 by using basic Q learning algorithm.

Primary LanguageJupyter Notebook

Reinforcement Learning: image

Q learning algo:
Q-Function
The Q-function uses the Bellman equation and takes state(s) and action(a) as input. The equation simplifies the state values and state-action value calculation.
image

Q-learning algorithm
image

Environment used:
Python: 3.8.10
gym: 0.26.2