Bryan Chan
Papers
1
Total Citations
7
H-Index
1
About
Bryan Chan is a rising researcher in artificial intelligence, with a primary focus on imitation learning and reinforcement learning. His most cited work, "Learning From Guided Play: Improving Exploration for Adversarial Imitation Learning With Simple Auxiliary Tasks" (2023), addresses a critical bottleneck in adversarial imitation learning (AIL)—the need for effective exploration during online reinforcement learning. Chan demonstrates that standard, naïve exploration strategies often fail, and proposes a novel framework that integrates simple auxiliary tasks to guide exploration, significantly improving policy learning efficiency. This contribution has already garnered attention, with 7 citations in a short time, signaling its impact on the field. Chan’s research bridges the gap between supervised and adversarial imitation learning, offering practical solutions to distribution shift and exploration challenges. His work is particularly valuable for students and researchers seeking to understand how to make AIL more robust and scalable in complex environments. As an emerging voice in AI, Chan is poised to make further contributions to autonomous decision-making and robot learning.
Research Focus
Key Achievements
Top Papers
- 1