Aspiration-based Reinforcement Learning

This work was conducted during my final year bachelor’s internship at the PIK (Potsdam Institute for Climate Impact Research) under the supervision of Jobst Heitzig.

There are three outputs from this project:

• A blog post on LessWrong, crossposted on the Alignment Forum, presenting the main ideas and the results of the project.
• An internship academic report providing a detailed presentation of the project, following the structure of a research paper.
• A GitHub repository that implements the algorithms presented in the report using the Stable Baselines3 framework.