Ted Moskovitz

According to our database, Ted Moskovitz authored at least 15 papers between 2018 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation.

Aaditya K. Singh, Ted Moskovitz, Felix Hill, Stephanie C. Y. Chan, Andrew M. Saxe

CoRR, 2024

2023

Confronting Reward Model Overoptimization with Constrained RLHF.

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

CoRR, 2023

The Transient Nature of Emergent In-Context Learning in Transformers.

Aaditya K. Singh, Stephanie C. Y. Chan, Ted Moskovitz, Erin Grant, Andrew M. Saxe, Felix Hill

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

A State Representation for Diminishing Rewards.

Ted Moskovitz, Samo Hromadka, Ahmed Touati, Diana Borsa, Maneesh Sahani

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs.

Ted Moskovitz, Brendan O'Donoghue, Vivek Veeriah, Sebastian Flennerhag, Satinder Singh, Tom Zahavy

Proceedings of the International Conference on Machine Learning, 2023

Minimum Description Length Control.

Ted Moskovitz, Ta-Chu Kao, Maneesh Sahani, Matt M. Botvinick

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Transfer RL via the Undo Maps Formalism.

Abhi Gupta, Ted Moskovitz, David Alvarez-Melis, Aldo Pacchiano

CoRR, 2022

A First-Occupancy Representation for Reinforcement Learning.

Ted Moskovitz, Spencer R. Wilson, Maneesh Sahani

Proceedings of the Tenth International Conference on Learning Representations, 2022

Towards an Understanding of Default Policies in Multitask Policy Optimization.

Ted Moskovitz, Michael Arbel, Jack Parker-Holder, Aldo Pacchiano

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Deep Reinforcement Learning with Dynamic Optimism.

Ted Moskovitz, Jack Parker-Holder, Aldo Pacchiano, Michael Arbel

CoRR, 2021

Tactical Optimism and Pessimism for Deep Reinforcement Learning.

Ted Moskovitz, Jack Parker-Holder, Aldo Pacchiano, Michael Arbel, Michael I. Jordan

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Efficient Wasserstein Natural Gradients for Reinforcement Learning.

Ted Moskovitz, Michael Arbel, Ferenc Huszar, Arthur Gretton

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

Amortised Learning by Wake-Sleep.

Li K. Wenliang, Theodore H. Moskovitz, Heishiro Kanagawa, Maneesh Sahani

Proceedings of the 37th International Conference on Machine Learning, 2020

2019

First-Order Preconditioning via Hypergradient Descent.

Ted Moskovitz, Rui Wang, Janice Lan, Sanyam Kapoor, Thomas Miconi, Jason Yosinski, Aditya Rawal

CoRR, 2019

2018

Feedback alignment in deep convolutional networks.

Theodore H. Moskovitz, Ashok Litwin-Kumar, L. F. Abbott

CoRR, 2018