430 citations · 471 across the 6 of their papers we have counts for
7 papers
Diversifying AI: Towards Creative Chess with AlphaZero
Tom Zahavy, Vivek Veeriah, Shaobo Hou +7
In recent years, Artificial Intelligence (AI) systems have surpassed human intelligence in a variety of computational tasks. However, AI systems, like humans, make mistakes, have b…
Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality
Tom Zahavy, Yannick Schroecker, Feryal Behbahani +4
Finding different solutions to the same problem is a key aspect of intelligence associated with creativity and adaptation to novel situations. In reinforcement learning, a set of d…
The Option Keyboard: Combining Skills in Reinforcement Learning
André Barreto, Diana Borsa, Shaobo Hou +8
The ability to combine known skills to create new ones may be crucial in the solution of complex reinforcement learning problems that unfold over extended periods. We argue that a…
Best of both worlds: local and global explanations with human-understandable concepts
Jessica Schrouff, Sebastien Baur, Shaobo Hou +6
Interpretability techniques aim to provide the rationale behind a model's decision, typically by explaining either an individual prediction (local explanation, e.g. 'why is this pa…
Discovering a set of policies for the worst case reward
Tom Zahavy, Andre Barreto, Daniel J Mankowitz +4
We study the problem of how to construct a set of policies that can be composed together to solve a collection of reinforcement learning tasks. Each task is a different reward func…
Concept-based model explanations for Electronic Health Records
Diana Mincu, Eric Loreaux, Shaobo Hou +7
Recurrent Neural Networks (RNNs) are often used for sequential modeling of adverse outcomes in electronic health records (EHRs) due to their ability to encode past clinical states.…
Underspecification Presents Challenges for Credibility in Modern Machine Learning
Alexander D'Amour, Katherine Heller, Dan Moldovan +37
ML models often exhibit unexpectedly poor behavior when they are deployed in real-world domains. We identify underspecification as a key reason for these failures. An ML pipeline i…