Speaker: Dr. Amrit Singh Bedi
From: University of Maryland
Abstract
Recent advancements in Artificial Intelligence (AI), such as AlphaZero and ChatGPT, have significantly impacted various fields. Reinforcement learning (RL) plays a crucial role in these achievements. However, deploying RL in real-world applications, including robotics, finance, and healthcare, presents challenges such as efficient exploration, scalability, domain adaptation, and safety. One key aspect common to all these challenges in RL is the design of effective reward functions, which are often assumed to be known but remain elusive in practice. In this talk, we will discuss our recent results in addressing these challenges, specifically focusing on sparse rewards in robotic applications. While designing sparse rewards may seem easier, it introduces significant exploration challenges that make traditional algorithms inefficient. To tackle this, we propose heavy-tailed policy gradient algorithms, which provide a promising solution. We derive precise sample complexity bounds for the proposed algorithms and demonstrate their effectiveness in both simulators and real robots.
Furthermore, we will shed light on the broader topic of reward design in RL through bilevel optimization and explore potential solutions. Additionally, we will discuss the relevance of similar ideas from RL in overcoming safety concerns when deploying Large Language Models (LLMs) such as ChatGPT effectively in real-world settings.
For more info, please follow this link.
Read More