Radu Marinescu

Confessions of a worldly software miner

2015 · Mining Software Repositories

Once upon a time I was an idealistic researcher. I started mining software order to spot and correct design flaws. Like any idealistic researcher, I was creating approaches, building prototypes, performing empirical studies, writing papers …

Iterative Reward Shaping using Human Feedback for Correcting Reward Misspecification

2023 · arXiv (Cornell University)

A well-defined reward function is crucial for successful training of an reinforcement learning (RL) agent. However, defining a suitable reward function is a notoriously challenging task, especially in complex, multi-objective environments. Developers often have to …