1.3k citations · 2.9k across the 32 of their papers we have counts for
6 papers · 1 filter
Domain Generalization for Robust Model-Based Offline Reinforcement Learning
Alan Clark, Shoaib Ahmed Siddiqui, Robert Kirk +3
Existing offline reinforcement learning (RL) algorithms typically assume that training data is either: 1) generated by a known policy, or 2) of entirely unknown origin. We consider…
Mechanistic Mode Connectivity
Ekdeep Singh Lubana, Eric J. Bigelow, Robert P. Dick +2
We study neural network loss landscapes through the lens of mode connectivity, the observation that minimizers of neural networks retrieved via training on a dataset are connected…
Broken Neural Scaling Laws
Ethan Caballero, Kshitij Gupta, Irina Rish +1
We present a smoothly broken power law functional form (that we refer to as a Broken Neural Scaling Law (BNSL)) that accurately models & extrapolates the scaling behaviors of deep…
Towards Out-of-Distribution Adversarial Robustness
Adam Ibrahim, Charles Guille-Escuret, Ioannis Mitliagkas +3
Adversarial robustness continues to be a major challenge for deep learning. A core issue is that robustness to one type of attack often fails to transfer to other attacks. While pr…
Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics
Shoaib Ahmed Siddiqui, Nitarshan Rajkumar, Tegan Maharaj +2
Modern machine learning research relies on relatively few carefully curated datasets. Even in these datasets, and typically in `untidy' or raw data, practitioners are faced with si…
Defining and Characterizing Reward Hacking
Joar Skalse, Nikolaus H. R. Howe, Dmitrii Krasheninnikov +1
We provide the first formal definition of reward hacking, a phenomenon where optimizing an imperfect proxy reward function leads to poor performance according to the true reward fu…