Victor Lesser Dissertation Award

The Victor Lesser Distinguished Dissertation Award is given for dissertations in the field of autonomous agents and multiagent systems that show originality, depth, impact, as well as quality of writing, supported by high-quality publications. The 2022 Victor Lesser Dissertation Award prize committee (Paolo Turrini (chair), Gita Sukthankar, F.P. (Fernando) Pascoal Dos Santos & Ann Nowé) has recommended the following recipient for the 2023 award.

Jiaoyang Li, whose thesis titled “Efficient and Effective Techniques for Large-Scale Multi-Agent Path Finding” was supervised by Sven Koenig at the University of Southern California.

Her work has impressed the committee for technical depth and real-world impact. The achievements on multi-agent path findings are ground-breaking with “new heuristics that can speed up the state-of-the-art optimal MAPF algorithm by up to 50 times; three symmetry-reasoning techniques and that can speed up the abovementioned algorithm and its variant with the admissible heuristics by up to 4 orders of magnitude”. 

Runner-up Award

Shangtong Zhang, whose thesis titled “Breaking the Deadly Triad in Reinforcement Learning” was supervised by Shimon Whiteson at the University of Oxford.

The work impressed the committee for its theoretical depth, with algorithms that address the instability of reinforcement learning, resulting from the combination of off-policy learning, function approximation, and bootstrapping. The proposed algorithms are computationally efficient and can be applicable to large scale scenarios. Some of the results originated from a first-authored publication that obtained a best paper award at AAMAS.