Yi-Chia Tseng

About

Yi-Chia Tseng is a researcher in artificial intelligence and machine learning, with a primary focus on reinforcement learning and inverse reinforcement learning. Her most-cited work, "An Efficient Unified Approach Using Demonstrations for Inverse Reinforcement Learning" (2019), addresses a fundamental challenge in the field: the difficulty of manually designing reward functions for complex reinforcement learning problems. Tseng proposes a unified framework that leverages expert demonstrations to efficiently infer reward functions, enabling agents to learn optimal policies without explicit reward engineering. This contribution has garnered 5 citations and is recognized for its practical impact on improving the autonomy and adaptability of AI systems. By streamlining the inverse reinforcement learning process, Tseng's research helps bridge the gap between theoretical algorithms and real-world applications, such as robotics and autonomous decision-making. Her work is notable for its focus on efficiency and scalability, making advanced reinforcement learning techniques more accessible. Tseng continues to explore how demonstration-based learning can enhance AI performance, positioning her as an emerging voice in the development of more intelligent and self-sufficient learning agents.

Research Focus

Key Achievements

Top Papers

1. 1
   An Efficient Unified Approach Using Demonstrations for Inverse Reinforcement Learning

   5 citations · 2019

Key Collaborators

Contact & Links