Nir Levine

Computer Science · Physical Sciences

14h-index2.0kcitations29works143.52yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Reinforcement Learning in Robotics(10), Domain Adaptation and Few-Shot Learning(7), Advanced Bandit Algorithms Research(6), Adversarial Robustness in Machine Learning(5), Data Stream Mining Techniques(4)

Publications27 total

Towards Responsible Development of Generative AI for Education: An Evaluation-Driven Approach
arXiv (Cornell University)·2024· 17 citedOpen Access
Task-agnostic Continual Learning with Hybrid Probabilistic Models
arXiv (Cornell University)·2021· 3 citedOpen Access
Task-agnostic Continual Learning with Hybrid Probabilistic Models
arXiv (Cornell University)·2021· 1 citedOpen Access
Challenges of real-world reinforcement learning: definitions, benchmarks and analysis
Machine Learning·2021· 528 citedOpen Access
Neural Rate Control for Video Encoding using Imitation Learning
arXiv (Cornell University)·2020Open Access
Balancing Constraints and Rewards with Meta-Gradient D4PG
arXiv (Cornell University)·2020· 6 citedOpen Access
Optimization and Generalization of Regularization-Based Continual Learning: a Loss Approximation Viewpoint
arXiv (Cornell University)·2020· 14 citedOpen Access
A maximum-entropy approach to off-policy evaluation in average-reward MDPs
arXiv (Cornell University)·2020Open Access
A maximum-entropy approach to off-policy evaluation in average-reward\n MDPs
arXiv (Cornell University)·2020Open Access
Robust Reinforcement Learning for Continuous Control with Model Misspecification
arXiv (Cornell University)·2020· 6 citedOpen Access
Improved Knowledge Distillation via Teacher Assistant
Proceedings of the AAAI Conference on Artificial Intelligence·2020· 116 citedOpen Access
An empirical investigation of the challenges of real-world reinforcement\n learning
arXiv (Cornell University)·2020· 50 citedOpen Access
An empirical investigation of the challenges of real-world reinforcement learning
arXiv (Cornell University)·2020· 52 citedOpen Access
Prediction, Consistency, Curvature: Representation Learning for Locally-Linear Control
arXiv (Cornell University)·2019· 8 citedOpen Access
Prediction, Consistency, Curvature: Representation Learning for\n Locally-Linear Control
arXiv (Cornell University)·2019· 5 citedOpen Access
Robust Reinforcement Learning for Continuous Control with Model Misspecification
arXiv (Cornell University)·2019· 38 citedOpen Access
An Extended Relevance Model for Session Search
2017· 16 cited
An Extended Relevance Model for Session Search
arXiv (Cornell University)·2017· 1 citedOpen Access
Shallow Updates for Deep Reinforcement Learning
arXiv (Cornell University)·2017· 10 citedOpen Access
Rotting Bandits
arXiv (Cornell University)·2017· 2 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Daniel J. Mankowitz(8), Mehrdad Farajtabar(6), Shie Mannor(6), Todd Hester(5), Ang Li(4), Timothy Mann(4), Gabriel Dulac-Arnold(3), Jerry Li(3), Cosmin Păduraru(3), Sven Gowal(3), Koby Crammer(3), Tom Zahavy(3), Dilan Görür(3), Nevena Lazic(3), Rae Jeong(2), Yuanyuan Shi(2), Jackie Kay(2), Abbas Abdolmaleki(2), Jost Tobias Springenberg(2), Martin Riedmiller(2)