Deep Reinforcement Learning
General overview: In this homework you will learn how to implement and test neural network models for solving reinforcement learning problems. The basic tasks for the homework will require to implement some extensions to the code that you have seen in the Lab. The advanced tasks will require to train and test your learning agent on a different type of input (image pixels) or Gym environment. You can just choose one of the advanced tasks to get the maximum grade. If you are interested in improving your skills, feel free to try both advanced tasks. Given the higher computational complexity of RL, in this homework you donβt need to tune learning hyperparameters using search procedures and cross-validation; however, you are encouraged to play with model hyperparameters to find a satisfactory configuration.
Technical notes: The homework should be implemented in Python using the PyTorch framework. The student can explore additional libraries and tools to implement the models; however, please make sure you understand the code you are writing because during the exam you might receive specific questions related to your implementation. The entire source code required to run the homework must be uploaded as a compressed archive in a Moodle section dedicated to the homework. If your code will be entirely included in a single Python notebook, just upload the notebook file.
Final report: Along with the source code, you must separately upload a PDF file containing a brief report of your homework. The report should include a brief Introduction on which you explain the homework goals and the main implementation strategies you choose, a brief Method section where you describe your model architectures and hyperparameters, and a Result section where you present the simulation results. Total length must not exceed 6 pages, though you can include additional tables and figures in a final Appendix (optional). The report must be self-contained, so please make sure that all relevant results are explicitly included in the report / notebook. Given the dynamical nature of RL problems, you can explore more sophisticated media for showing the results of your model (e.g., animated GIFs or short movies).
