This paper presents the development and evaluation of an autonomous agent based on reinforcement learning (RL) that learns to play a 2D platformer game. Designed in Unity and trained using the Unity ML-Agents Toolkit, the environment integrates a variety of procedural obstacles and traps to provide realistic challenges and measure learning adaptability. Two RL algorithms, Proximal Policy Optimization (PPO) and Soft ActorCritic (SAC), were trained using identical conditions for fair comparison. Quantitative results show that SAC converged faster and achieved higher average rewards early on, whereas PPO learned more slowly but with a steadier improvement in performance. These findings are evaluated statistically, and potential future extensions (such as procedural level generation and combined learning methods) are discussed.