BeNeRL Seminar Series


The BeNeRL Seminar Series are monthly online talks by RL researchers from all over the world. The intention is to primarily give a platform to advanced PhD students and early career researchers to 1) display their work and 2) share their practical RL experience (i.e., how do you manage large-scale RL experiments as a new researcher in the field, a topic that is often skipped in talks). We maintain a summary of the main advice on experimentation.


The seminar is online and takes place on every second Thursday of the month, 16.00-17.00 (CET)
(unless there is a conflict with an important machine learning conference, when we try to shift by one week)


Upcoming Speaker: Hojoon Lee (KAIST AI)


(ZOOM LINK: CLICK HERE )

Date: December 19, 16.00-17.00 (CET)

Title: Designing Neural Network Architecture for Deep Reinforcement Learning 

Link: Zoom Link - Click Here

Abstract: While scaling laws have accelerated breakthroughs in computer vision and language modeling, their effects are less predictable in reinforcement learning (RL), where simply “scaling up” data, parameters, and computations rarely guarantees better results. In this talk, I will explore the barriers that make scaling challenging in RL and introduce new architectural designs that alleviate these challenges. I will also discuss future research opportunities that can improve scaling laws in RL. 

Schedule


Talks are always online and take place between 16.00-17.00 (CET).




2023




2024











2025


If you have any questions about the seminar series, feel free to contact:


Zhao Yang: z.yang(at)liacs.leidenuniv.nl


Thomas Moerland