ML Anthology

Moskovitz, Ted

13 publications

ICML 2025 Strategy Coopetition Explains the Emergence and Transience of In-Context Learning Aaditya K Singh, Ted Moskovitz, Sara Dragutinović, Felix Hill, Stephanie C.Y. Chan, Andrew M Saxe
ICLR 2024 Confronting Reward Model Overoptimization with Constrained RLHF Ted Moskovitz, Aaditya K Singh, Dj Strouse, Tuomas Sandholm, Ruslan Salakhutdinov, Anca Dragan, Stephen Marcus McAleer
ICML 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
NeurIPS 2023 A State Representation for Diminishing Rewards Ted Moskovitz, Samo Hromadka, Ahmed Touati, Diana Borsa, Maneesh Sahani
NeurIPSW 2023 Confronting Reward Model Overoptimization with Constrained RLHF Ted Moskovitz, Aaditya Singh, Dj Strouse, Tuomas Sandholm, Ruslan Salakhutdinov, Anca Dragan, Stephen McAleer
ICLR 2023 Minimum Description Length Control Ted Moskovitz, Ta-Chu Kao, Maneesh Sahani, Matthew Botvinick
ICML 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
NeurIPS 2023 The Transient Nature of Emergent In-Context Learning in Transformers Aaditya Singh, Stephanie Chan, Ted Moskovitz, Erin Grant, Andrew Saxe, Felix Hill
ICMLW 2023 Undo Maps: A Tool for Adapting Policies to Perceptual Distortions Abhi Gupta, Ted Moskovitz, David Alvarez-Melis, Aldo Pacchiano
AISTATS 2022 Towards an Understanding of Default Policies in Multitask Policy Optimization Ted Moskovitz, Michael Arbel, Jack Parker-Holder, Aldo Pacchiano
ICLR 2022 A First-Occupancy Representation for Reinforcement Learning Ted Moskovitz, Spencer R Wilson, Maneesh Sahani
ICLR 2021 Efficient Wasserstein Natural Gradients for Reinforcement Learning Ted Moskovitz, Michael Arbel, Ferenc Huszar, Arthur Gretton
NeurIPS 2021 Tactical Optimism and Pessimism for Deep Reinforcement Learning Ted Moskovitz, Jack Parker-Holder, Aldo Pacchiano, Michael Arbel, Michael I. Jordan