Hardware: Google Colab T4

• Set ent_coef for PPO as it encourages exploration of other actions. Stable Baselines3 defaults the value to 0.0. More Information
• Do not set your eval_freq too low, as it can sometimes cause instability during learning due to being interrupted by evaluation. (e.g. >=10,000)
• Stable Baseline3's DQN parameters exploration_initial_eps and exploration_final_eps help determine how exploratory your model is at the beginning and end of training.

• Solving Gymnasium's Lunar Lander with Deep Q Learning (DQN)
• Comparing how PPO, SAC, and DQN Perform on Gymnasium's Lunar Lander