Deep Q-Learning for CartPole-v0

This repository contains a Python implementation of a Deep Q-Learning (DQN) agent trained on the OpenAI Gym's CartPole-v0 environment. The agent uses a neural network to approximate the Q-function and employs epsilon-greedy policy for exploration and exploitation.

Techniques and Resources Used Deep Q-Learning (DQN): Implementing DQN using PyTorch for training an agent to balance a pole on a moving cart.

Replay Memory: Utilizing a replay memory buffer to store and sample experiences for more stable training.

Target Network: Implementing a target network to stabilize the training process.

Epsilon-Greedy Policy: Employing an epsilon-greedy policy for a balance between exploration and exploitation.