Ted Moskovitz
11 papers · 2021–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (25) π Conference Polyglot Β· Bronze π Triple Crown ποΈ Keyword Collector (50)
π₯
Unstoppable Β· Bronze
β
The Questioner
π
Century Club Β· Bronze
Venues
Top co-authors
Research topics
Machine Learning
(9)
Artificial Intelligence
(6)
Learning Types Β· Machine Learning
(6)
Reinforcement Learning
(5)
Core AI
(5)
Optimization & Theory
(5)
Methods
(4)
Deep Learning
(3)
Core Methods
(2)
Learning Types Β· Deep Learning
(2)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Applications
(1)
Architectures
(1)
Bayesian & Probabilistic
(1)
Keywords
reinforcement learning
(4)
multi-task reinforcement learning
(2)
continuous control
(2)
state representation
(2)
in-context learning
(2)
successor representation
(2)
policy gradient
(2)
subcircuits
(2)
policy optimization
(1)
reward modeling
(1)
multi-task learning
(1)
neural network optimization
(1)
constrained optimization
(1)
natural gradient
(1)
epistemic uncertainty
(1)
minimum description length
(1)
neural network training
(1)
l2 regularization
(1)
off-policy learning
(1)
bayesian inference
(1)
Papers
Strategy Coopetition Explains the Emergence and Transience of In-Context Learning
ICML 2025
Confronting Reward Model Overoptimization with Constrained RLHF
ICLR 2024
What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation
ICML 2024
A State Representation for Diminishing Rewards
NeurIPS 2023
Minimum Description Length Control
ICLR 2023
ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs
ICML 2023
The Transient Nature of Emergent In-Context Learning in Transformers
NeurIPS 2023
A First-Occupancy Representation for Reinforcement Learning
ICLR 2022
Towards an Understanding of Default Policies in Multitask Policy Optimization
AISTATS 2022
Efficient Wasserstein Natural Gradients for Reinforcement Learning
ICLR 2021
Tactical Optimism and Pessimism for Deep Reinforcement Learning
NeurIPS 2021