Yogesh Tripathi

I am currently a Master’s student in Artificial Intelligence and Machine Learning at TU Darmstadt. My primary interests lie in Reinforcement Learning and Multimodal AI. For my Master’s thesis, I am working on sample-efficient off-policy reinforcement learning methods under the supervision of Théo Vincent. We also explored sparsity in deep RL agents, which resulted in a publication at the Reinforcement Learning Conference 2025: Eau De Q-Network: Adaptive Distillation of Neural Networks in Deep Reinforcement Learning (https://arxiv.org/pdf/2503.01437). During my studies, I also had the opportunity to work as a research assistant at DFKI, where I developed slimDQN (https://github.com/theovincent/slimDQN), a minimal library for Deep Q-Learning, primarily designed for RL research. I was awarded the Robot Learning Expert Certificate by Prof. Jan Peters after completing both theory and project components of the Robot Learning course at TU Darmstadt.