ECE Seminar - Discovering Agent-Centric Latent States in Theory and in Practice
Supporting the below United Nations Sustainable Development Goals:支持以下聯合國可持續發展目標：支持以下联合国可持续发展目标：
A latent state can enable vastly better planning, exploration, and credit assignment by keeping task-relevant information while discarding distractions and irrelevant details. For example, in video games, there is a game-engine state which has all relevant information for the underlying dynamics. This tutorial will discuss how we can discover such a latent state in the real world directly from observations, and the kinds of latent states which are known to be discoverable. The tutorial discusses theoretical developments at a high-level, to explain the key pieces of understanding as well as their limitations. The talk will discuss where the state-of-the-art is experimentally, and what is currently ready for usage in real-world applications.
Alex Lamb is an Assistant Professor at Tsinghua University AI College and a former senior researcher in the AI Frontiers group at Microsoft. He completed his PhD under Yoshua Bengio and has worked on deep learning, generative models, reinforcement learning, and sequence models. He also worked on deep learning for classical Japanese document recognition as well as demand forecasting systems at Amazon.