Alert button
Picture for DJ Strouse

DJ Strouse

Alert button

Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs

Feb 22, 2024
Aaditya K. Singh, DJ Strouse

Viaarxiv icon

Confronting Reward Model Overoptimization with Constrained RLHF

Oct 10, 2023
Ted Moskovitz, Aaditya K. Singh, DJ Strouse, Tuomas Sandholm, Ruslan Salakhutdinov, Anca D. Dragan, Stephen McAleer

Viaarxiv icon

Melting Pot 2.0

Dec 13, 2022
John P. Agapiou, Alexander Sasha Vezhnevets, Edgar A. Duéñez-Guzmán, Jayd Matyas, Yiran Mao, Peter Sunehag, Raphael Köster, Udari Madhushani, Kavya Kopparapu, Ramona Comanescu, DJ Strouse, Michael B. Johanson, Sukhdeep Singh, Julia Haas, Igor Mordatch, Dean Mobbs, Joel Z. Leibo

Figure 1 for Melting Pot 2.0
Figure 2 for Melting Pot 2.0
Figure 3 for Melting Pot 2.0
Figure 4 for Melting Pot 2.0
Viaarxiv icon

In-context Reinforcement Learning with Algorithm Distillation

Oct 25, 2022
Michael Laskin, Luyu Wang, Junhyuk Oh, Emilio Parisotto, Stephen Spencer, Richie Steigerwald, DJ Strouse, Steven Hansen, Angelos Filos, Ethan Brooks, Maxime Gazeau, Himanshu Sahni, Satinder Singh, Volodymyr Mnih

Figure 1 for In-context Reinforcement Learning with Algorithm Distillation
Figure 2 for In-context Reinforcement Learning with Algorithm Distillation
Figure 3 for In-context Reinforcement Learning with Algorithm Distillation
Figure 4 for In-context Reinforcement Learning with Algorithm Distillation
Viaarxiv icon

Semantic Exploration from Language Abstractions and Pretrained Representations

Apr 08, 2022
Allison C. Tam, Neil C. Rabinowitz, Andrew K. Lampinen, Nicholas A. Roy, Stephanie C. Y. Chan, DJ Strouse, Jane X. Wang, Andrea Banino, Felix Hill

Figure 1 for Semantic Exploration from Language Abstractions and Pretrained Representations
Figure 2 for Semantic Exploration from Language Abstractions and Pretrained Representations
Figure 3 for Semantic Exploration from Language Abstractions and Pretrained Representations
Figure 4 for Semantic Exploration from Language Abstractions and Pretrained Representations
Viaarxiv icon

Collaborating with Humans without Human Data

Oct 15, 2021
DJ Strouse, Kevin R. McKee, Matt Botvinick, Edward Hughes, Richard Everett

Figure 1 for Collaborating with Humans without Human Data
Figure 2 for Collaborating with Humans without Human Data
Figure 3 for Collaborating with Humans without Human Data
Figure 4 for Collaborating with Humans without Human Data
Viaarxiv icon

Learning more skills through optimistic exploration

Jul 29, 2021
DJ Strouse, Kate Baumli, David Warde-Farley, Vlad Mnih, Steven Hansen

Figure 1 for Learning more skills through optimistic exploration
Figure 2 for Learning more skills through optimistic exploration
Figure 3 for Learning more skills through optimistic exploration
Figure 4 for Learning more skills through optimistic exploration
Viaarxiv icon

A Neural Architecture for Designing Truthful and Efficient Auctions

Jul 11, 2019
Andrea Tacchetti, DJ Strouse, Marta Garnelo, Thore Graepel, Yoram Bachrach

Figure 1 for A Neural Architecture for Designing Truthful and Efficient Auctions
Figure 2 for A Neural Architecture for Designing Truthful and Efficient Auctions
Figure 3 for A Neural Architecture for Designing Truthful and Efficient Auctions
Viaarxiv icon