In this project I have implemented and tested neural network models for solving reinforcement learning problems.
- Create and tune a deep reinforcement model in order to control the CartPole environment. Tune the exploration profile (either using eps-greedy or softmax) to improve the learning curve. Tune the model hyperparameters or tweak the reward function in order to speed-up learning convergence (i.e., reach the same accuracy with fewer training episodes).
- Create and tune a deep reinforcement model in order to control the CartPole environment using directly the screen pixels, rather than the compact state representation (cart position, cart velocity, pole angle, pole angular velocity).
- Train a deep RL agent on a different Gym environment.
A detailed report is present in the nn_homework_03.pdf file