7 papers
Open Problems in Constitutional Preference Reconstruction
Eleanor Clifford, Michael Amir, Arduin Findeis +2
Pairwise preference data is widely used for training and evaluating language models (e.g., RLHF), but each datapoint records a \emph{choice}, not the rationale behind it. Methods s…
Scaling Multi-Agent Environment Co-Design with Diffusion Models
Hao Xiang Li, Michael Amir, Amanda Prorok
The agent-environment co-design paradigm jointly optimises agent policies and environment configurations in search of improved system performance. With application domains ranging…
Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfinding
Rishabh Jain, Keisuke Okumura, Michael Amir +2
Multi-Agent Path Finding (MAPF) is a representative multi-agent coordination problem, where multiple agents are required to navigate to their respective goals without collisions. S…
When Is Diversity Rewarded in Cooperative Multi-Agent Learning?
Michael Amir, Matteo Bettini, Amanda Prorok
The success of teams in robotics, nature, and society often depends on the division of labor among diverse specialists; however, a principled explanation for when such diversity su…
Remotely Detectable Robot Policy Watermarking
Michael Amir, Manon Flageat, Amanda Prorok
The success of machine learning for real-world robotic systems has created a new form of intellectual property: the trained policy. This raises a critical need for novel methods th…
Graph Attention-Guided Search for Dense Multi-Agent Pathfinding
Rishabh Jain, Keisuke Okumura, Michael Amir +1
Finding near-optimal solutions for dense multi-agent pathfinding (MAPF) problems in real-time remains challenging even for state-of-the-art planners. To this end, we develop a hybr…