[The 44th TrustML Young Scientist Seminar]

Fri, 09 Dec 2022 19:00 - 20:00 JST
Online Link visible to participants

Registration is closed

Get invited to future events

Free admission
-Passcode sBQ5r635NF -Time Zone:JST -The seats are available on a first-come-first-served basis. -When the seats are fully booked, we may stop accepting applications. -Simultaneous interpretation will not be available.


The TrustML Young Scientist Seminars (TrustML YSS) started from January 28, 2022.

The TrustML YSS is a video series that features young scientists giving talks and discoveries in relation with Trustworthy Machine Learning.

Timetable for the TrustML YSS online seminars from Nov. to Dec. 2022.

For more information please see the following site.

This network is funded by RIKEN-AIP's subsidy and JST, ACT-X Grant Number JPMJAX21AF, Japan.

【The 44th Seminar】

Date and Time: Dec. 9th 7:00 pm - 8:00 pm(JST)

Venue: Zoom webinar

Language: English

Speaker: Ezgi Korkma (DeepMind)
Title: Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPs
The use of deep neural networks as function approximators has led to striking progress for reinforcement learning algorithms and applications. Yet the knowledge we have on decision boundary geometry and the loss landscape of neural policies is still quite limited. In this paper, we propose a framework to investigate the decision boundary and loss landscape similarities across states and across MDPs. We conduct experiments in various games from the Arcade Learning Environment, and discover that high sensitivity directions for neural policies are correlated across MDPs. We argue that these high sensitivity directions support the hypothesis that non-robust features are shared across training environments of reinforcement learning agents. We believe our results reveal fundamental properties of the environments used in deep reinforcement learning training, and represent a tangible step towards building robust and reliable deep reinforcement learning agents.

All participants are required to agree with the AIP Seminar Series Code of Conduct.
Please see the URL below.

RIKEN AIP will expect adherence to this code throughout the event. We expect cooperation from all participants to help ensure a safe environment for everybody.

About this community



Public events of RIKEN Center for Advanced Intelligence Project (AIP)

Join community