Events Calendar

PhD Thesis Proposal - Grace Zhang

Title: Knowledge Transfer for Data Efficient Reinforcement Learning
 
 
 
Committee : Gaurav Sukatme (Chair), Stefanos Nikolaidis, Erdem Biyik, Daniel Seita, Stephen Tu
 
 
Abstract:  Reinforcement learning and the closely related inverse reinforcement learning problems are general and powerful frameworks to learn sequential decision making tasks with only a reward function or demonstrations and minimal assumptions on the environment. However, the trade-off is that these algorithms can be very data inefficient, in the number of trials required in the training environment or the number of demonstrations required.  In my work I explore how to achieve more data efficient learning through knowledge transfer between environments or between tasks.  Specifically, on how to transfer behaviors between environments, how to share behaviors between tasks in multi-task RL, and how to utilize multi-task information to do inverse RL from limited demonstrations.
 

Location: Ginsburg Hall (GCS) - 402C - 4th Floor

Audiences: Everyone Is Invited

Contact: Ellecia Williams

This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.

Add to Google Calendar