This project implements a reinforcement learning algorithm called Q-learning to solve the Frozen Lake problem in the OpenAI Gym environment. The Frozen Lake problem is a simple gridworld problem where the agent needs to navigate through a grid of frozen and slippery tiles to reach a goal tile. The agent receives a reward of 1 when it reaches the goal tile and a reward of 0 for all other actions. The goal of the agent is to learn the optimal policy that leads to the goal tile with the maximum reward.
To run the project, follow these steps:
- Clone the repository
git clone https://github.com/SynaSpike/Reinforcement-Learning.git
- Install the required packages
pip install -r requirements.txt
python FrozenLake_QLearning.py
This will generates the Q_table and display the Agents finding its path on the Frozen Lake environment.
