Reinforcement Learning Agent Test

This project demonstrates a basic implementation of reinforcement learning algorithms using Python. It tests agent behavior in various environments to evaluate learning performance and adaptation through reward-based training.

Features

• Reinforcement Learning Algorithms: Implements foundational RL techniques such as Q-learning and Deep Q-Networks (DQN).
• Customizable Environments: Supports simulation in multiple environments for agent training.
• Performance Monitoring: Tracks agent performance and improvements over time.

Technologies Used

• Python: Core language for the project.
• OpenAI Gym: Used to provide training environments for the agent.
• TensorFlow/PyTorch: For building and training neural networks.

How to Use

1. Clone the repository:

   git clone https://github.com/JulianFisla/reinforcement-learning-agent-test.git

2. Install the necessary dependencies:

   pip install -r requirements.txt

3. Run the training scripts (first the random agent):

   python random_agent.py

4. Run the training scripts (then the intelligent agent):

   python intelligent_agent.py

Known Issues:

1. Some environments may require additional dependencies.