University of Toronto September-December 2023 In this project, I explored how reinforcement learning (RL) agents simulate goal-directed behavior and whether they can be understood as morally intelligent systems. I implemented two core RL algorithms—Sarsa (on-policy) and Q-learning (off-policy)—in a custom gridworld using MATLAB. I then trained and analyzed both model-based and model-free agents in the classic cart-pole balancing task, comparing performance under…