Kavosh Asadi

Computer Science · Physical Sciences

10h-index651citations36works0.02yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

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

Research Topics

Reinforcement Learning in Robotics(24), Adversarial Robustness in Machine Learning(6), Evolutionary Algorithms and Applications(6), Advanced Bandit Algorithms Research(5), Topic Modeling(4)

Publications36 total

InstructVTON: Optimal Auto-Masking and Natural-Language-Guided Interactive Style Control for Inpainting-Based Virtual Try-On
arXiv (Cornell University)·2025Open Access
C2-DPO: Constrained Controlled Direct Preference Optimization
arXiv (Cornell University)·2025Open Access
Adjoint sharding for very long context training of state space models
arXiv (Cornell University)·2025Open Access
Learning the Target Network in Function Space
arXiv (Cornell University)·2024Open Access
TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
arXiv (Cornell University)·2023Open Access
Resetting the Optimizer in Deep RL: An Empirical Study
arXiv (Cornell University)·2023· 3 citedOpen Access
TD Convergence: An Optimization Perspective
arXiv (Cornell University)·2023Open Access
Characterizing the Action-Generalization Gap in Deep Q-Learning
arXiv (Cornell University)·2022· 1 citedOpen Access
Faster Deep Reinforcement Learning with Slower Online Network
arXiv (Cornell University)·2021· 1 citedOpen Access
Coarse-Grained Smoothness for RL in Metric Spaces
arXiv (Cornell University)·2021Open Access
Convergence of a Human-in-the-Loop Policy-Gradient Algorithm With Eligibility Trace Under Reward, Policy, and Advantage Feedback
arXiv (Cornell University)·2021Open Access
Deep Radial-Basis Value Functions for Continuous Control
Proceedings of the AAAI Conference on Artificial Intelligence·2021· 11 citedOpen Access
Lipschitz Lifelong Reinforcement Learning
Proceedings of the AAAI Conference on Artificial Intelligence·2021· 6 citedOpen Access
Continuous Doubly Constrained Batch Reinforcement Learning
arXiv (Cornell University)·2021· 6 citedOpen Access
Smoothness in Reinforcement Learning with Large State and Action Spaces
2021
Learning State Abstractions for Transfer in Continuous Control
arXiv (Cornell University)·2020· 3 citedOpen Access
Deep Radial-Basis Value Functions for Continuous Control
arXiv (Cornell University)·2020· 5 citedOpen Access
Deep RBF Value Functions for Continuous Control.
2020· 1 cited
DeepMellow: Removing the Need for a Target Network in Deep Q-Learning
2019· 61 citedOpen Access
State Abstraction as Compression in Apprenticeship Learning
Proceedings of the AAAI Conference on Artificial Intelligence·2019· 35 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Michael L. Littman(21), George Konidaris(9), Rasool Fakoor(6), Dipendra Misra(5), Shoham Sabach(5), J. D. Williams(4), David Abel(4), Cameron Allen(4), Geoffrey Zweig(3), Seungchan Kim(3), Ronald Parr(3), Evan Cater(3), Omer Gottesman(3), Xinyu Xu(3), Karim Bouyarmane(3), Dilip Arumugam(2), Yuu Jinnai(2), Melrose Roderick(2), Abdelrahman Mohamed(2), Neev Parikh(2)