Select a calendar:
Filter February Events by Event Type:
Events for February 05, 2024
Mon, Feb 05, 2024 @ 10:00 AM - 04:00 PM
Viterbi School of Engineering Career Connections
Receptions & Special Events
What is a Trojan Talk?
-1-hour-long company information sessions (on-campus or virtual)
-Great way to explore an organization or an industry.
-Gain insight into open positions and the history, culture, and values of the organization.
What is a Product Demo?
-1-hour-long company information sessions.
-Employers demonstrate a company product or service showcase.
Experience a unique opportunity to witness the product in action and gain comprehensive insights into the organization. Pre-registration required on Viterbi Career Gateway: https://viterbicareers.usc.edu/students/gateway/ > Events > Information Sessions For the most up-to-date information, visit the Career & Internship Expo Website: https://viterbicareers.usc.edu/careerexpo/
Audiences: All Viterbi
Contact: RTH 218 Viterbi Career Connections
Event Link: https://viterbicareers.usc.edu/careerexpo/
Mon, Feb 05, 2024 @ 10:00 AM - 01:00 PM
Viterbi School of Engineering Student Affairs
Workshops & Infosessions
Viterbi Ph.D. students are invited to stop by the EiS Communications Hub for one-on-one instruction for their academic and professional communications tasks. All instruction is provided by Viterbi faculty at the Engineering in Society Program.
Audiences: Viterbi Ph.D. Students
Contact: Helen Choi
Mon, Feb 05, 2024 @ 04:00 PM - 06:00 PM
Thomas Lord Department of Computer Science
Thesis Proposal: Ayush Jain
Date: February 5, 2024 (Monday), 4 pm - 6 pm
Committee: Erdem Biyik, Joseph J Lim, Gaurav Sukhatme, Stefanos Nikolaidis, Fefei Qian
Title: Enabling Robust Reinforcement Learning in Challenging Action Spaces
Abstract: The action space of an agent defines its interface to interact with the world. It can take two forms: discrete, as in recommender systems making decisions from millions of choices, or continuous, as in robots actuating control movements. While humans excel at a vast range of action spaces, from deciding between potentially unseen choices to making precise dexterous control like in surgery, conventional reinforcement learning (RL) is limited to simple action spaces beyond which agents fail entirely. Concretely, discrete RL typically assumes a "static" action space that never changes, while continuous RL assumes a "smooth" action space such that nearby actions have similar consequences. My goal is to alleviate these assumptions to broaden the applicability of RL agents to tasks with challenging action spaces. Thus, I build discrete RL algorithms that can adapt to any available action set and even choose from actions never seen before, such as recommending new items and choosing from unseen toolsets. In continuous action space tasks like robotics, I show how conventional agents get stuck on suboptimal actions due to a challenging action space. To address this, I propose a novel actor-critic algorithm enabling actors to search for more optimal actions.
Audiences: Everyone Is Invited
Contact: CS Events