Overview
Implementation of various Reinforcement Learning algorithms using OpenAI Gym (University Research Project).
This project involved studying and implementing classic Deep Reinforcement Learning algorithms to solve control tasks.
I implemented algorithms such as Deep Q-Network (DQN) and Proximal Policy Optimization (PPO) using PyTorch and trained agents in OpenAI Gym environments.
Through this project, I developed a strong grasp of Reinforcement Learning concepts including policies, value functions, and reward systems, and gained practical experience in training and debugging neural networks for dynamic environments.
