Ted Moskovitz - RankMe

26 papers A* 10A 1Journal 15

Year	Rank	Type	Title / Venue / Authors
2025	A*	`conf`	Strategy Coopetition Explains the Emergence and Transience of In-Context Learning. ICML Aaditya K. Singh, Ted Moskovitz, Sara Dragutinovic, Felix Hill, Stephanie C. Y. Chan, Andrew M. Saxe
2025	J	`jnl`	Strategy Coopetition Explains the Emergence and Transience of In-Context Learning. CoRR Aaditya K. Singh, Ted Moskovitz, Sara Dragutinovic, Felix Hill, Stephanie C. Y. Chan, Andrew M. Saxe
2024	A*	`conf`	Confronting Reward Model Overoptimization with Constrained RLHF. ICLR Ted Moskovitz, Aaditya K. Singh, DJ Strouse, Tuomas Sandholm, Ruslan Salakhutdinov, Anca D. Dragan, Stephen Marcus McAleer
2024	J	`jnl`	HARP: A challenging human-annotated math reasoning benchmark. CoRR Albert S. Yue, Lovish Madaan, Ted Moskovitz, DJ Strouse, Aaditya K. Singh
2024	J	`jnl`	Understanding dual process cognition via the minimum description length principle. PLoS Comput. Biol. Ted Moskovitz, Kevin J. Miller, Maneesh Sahani, Matthew M. Botvinick
2024	A*	`conf`	What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation. ICML Aaditya K. Singh, Ted Moskovitz, Felix Hill, Stephanie C. Y. Chan, Andrew M. Saxe
2024	J	`jnl`	What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation. CoRR Aaditya K. Singh, Ted Moskovitz, Felix Hill, Stephanie C. Y. Chan, Andrew M. Saxe
2023	A*	`conf`	A State Representation for Diminishing Rewards. NeurIPS Ted Moskovitz, Samo Hromadka, Ahmed Touati, Diana Borsa, Maneesh Sahani
2023	J	`jnl`	A State Representation for Diminishing Rewards. CoRR Ted Moskovitz, Samo Hromadka, Ahmed Touati, Diana Borsa, Maneesh Sahani
2023	J	`jnl`	Confronting Reward Model Overoptimization with Constrained RLHF. CoRR Ted Moskovitz, Aaditya K. Singh, DJ Strouse, Tuomas Sandholm, Ruslan Salakhutdinov, Anca D. Dragan, Stephen McAleer
2023	A*	`conf`	Minimum Description Length Control. ICLR Ted Moskovitz, Ta-Chu Kao, Maneesh Sahani, Matt M. Botvinick
2023	A*	`conf`	ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs. ICML Ted Moskovitz, Brendan O'Donoghue, Vivek Veeriah, Sebastian Flennerhag, Satinder Singh, Tom Zahavy
2023	J	`jnl`	ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs. CoRR Ted Moskovitz, Brendan O'Donoghue, Vivek Veeriah, Sebastian Flennerhag, Satinder Singh, Tom Zahavy
2023	A*	`conf`	The Transient Nature of Emergent In-Context Learning in Transformers. NeurIPS Aaditya K. Singh, Stephanie C. Y. Chan, Ted Moskovitz, Erin Grant, Andrew M. Saxe, Felix Hill
2023	J	`jnl`	The Transient Nature of Emergent In-Context Learning in Transformers. CoRR Aaditya K. Singh, Stephanie C. Y. Chan, Ted Moskovitz, Erin Grant, Andrew M. Saxe, Felix Hill
2022	A*	`conf`	A First-Occupancy Representation for Reinforcement Learning. ICLR Ted Moskovitz, Spencer R. Wilson, Maneesh Sahani
2022	J	`jnl`	Minimum Description Length Control. CoRR Ted Moskovitz, Ta-Chu Kao, Maneesh Sahani, Matthew M. Botvinick
2022	A	`conf`	Towards an Understanding of Default Policies in Multitask Policy Optimization. AISTATS Ted Moskovitz, Michael Arbel, Jack Parker-Holder, Aldo Pacchiano
2022	J	`jnl`	Transfer RL via the Undo Maps Formalism. CoRR Abhi Gupta, Ted Moskovitz, David Alvarez-Melis, Aldo Pacchiano
2021	J	`jnl`	A First-Occupancy Representation for Reinforcement Learning. CoRR Ted Moskovitz, Spencer R. Wilson, Maneesh Sahani
2021	J	`jnl`	Deep Reinforcement Learning with Dynamic Optimism. CoRR Ted Moskovitz, Jack Parker-Holder, Aldo Pacchiano, Michael Arbel
2021	A*	`conf`	Efficient Wasserstein Natural Gradients for Reinforcement Learning. ICLR Ted Moskovitz, Michael Arbel, Ferenc Huszar, Arthur Gretton
2021	A*	`conf`	Tactical Optimism and Pessimism for Deep Reinforcement Learning. NeurIPS Ted Moskovitz, Jack Parker-Holder, Aldo Pacchiano, Michael Arbel, Michael I. Jordan
2021	J	`jnl`	Towards an Understanding of Default Policies in Multitask Policy Optimization. CoRR Ted Moskovitz, Michael Arbel, Jack Parker-Holder, Aldo Pacchiano
2020	J	`jnl`	Efficient Wasserstein Natural Gradients for Reinforcement Learning. CoRR Ted Moskovitz, Michael Arbel, Ferenc Huszar, Arthur Gretton
2019	J	`jnl`	First-Order Preconditioning via Hypergradient Descent. CoRR Ted Moskovitz, Rui Wang, Janice Lan, Sanyam Kapoor, Thomas Miconi, Jason Yosinski, Aditya Rawal