Using reinforcement learning (RL), specifically Truncated Quantile Critics (TQC) and Deep Deterministic Policy Gradient (DDPG), to solve the Fetch environments in Gymnasium Robotics

Train an RL agent to master Atari's Pong with sparse rewards and high-dimensional inputs. Explore preprocessing, replay buffers, and performance-boosting strategies

Learn how to apply reinforcement learning to solve Gymnasium's Car Racing game, see how different algorithms perform, and explore whether discrete or continuous action spaces are better.

Explore how different On-Policy and Off-Policy reinforcement learning algorithms perform on Gymnasium's Lunar Lander

Learn how the Reinforcement Learning Algorithm Deep Q Learning (DQN) works and apply it to solve Gymnasium's Lunar Lander