Augmenting Decision with Hypothesis in Reinforcement Learning Speaker (s):  NGUYEN Minh Quang
PhD Student
School of Computing and Information Systems
Singapore Management University | Date: Time: Venue: | | 4 July 2024, Thursday 3:00pm – 3:30pm Meeting room 4.4, Level 4
School of Computing and Information Systems 1,
Singapore Management University,
80 Stamford Road, Singapore 178902 We look forward to seeing you at this research seminar. Please register by 3 July 2024. 
|
|
About the Talk
Value-based reinforcement learning is the current State-Of-The-Art due to high sampling efficiency. However, our theoretical and empirical studies show evidence that it suffers from low exploitation in early training period and bias sensitiveness. To address these issues, we propose to augment the decision-making process with hypothesis, a weak form of environment description. Our approach relies on prompting the learning agent with accurate hypotheses and designing a ready-to-adapt policy through incremental learning. We propose the ALH algorithm, showing detailed analyses on a typical learning scheme and a diverse set of Mujoco benchmarks.
This is a Pre-Conference talk for The Forty-first International Conference on Machine Learning (ICML 2024).
About the Speaker
NGUYEN Minh Quang is a PhD student at the School of Computing and Information Systems , Singapore Management University, under the supervision of Professor Hady W. Lauw. His research focuses on Reinforcement Learning problems.
