Ilya Kostrikov

I'm a Postdoctoral Scholar at UC Berkeley Artificial Intelligence Research lab, where I work on Deep Reinforcement Learning. In particular, I'm interested in sample efficiency, Offline RL, and finetuning after Offline RL pretraining.

I received my PhD from NYU, where I worked on sample efficient imitation and reinforcement learning. I did an internship at Facebook AI Research, several internships at Google Brain, and I participated in Google Student Research Advising Program.

Email / Google Scholar / GitHub / Twitter

Representative publications

A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning

Laura Smith*, Ilya Kostrikov*, Sergey Levine

Offline Reinforcement Learning with Implicit Q-Learning

I. Kostrikov, A. Nair, S. Levine

ICLR 2022

Automatic Data Augmentation for Generalization in Deep Reinforcement Learning

R. Raileanu, M. Goldstein, D. Yarats, I. Kostrikov, R. Fergus

NeurIPS 2021

Offline Reinforcement Learning with Fisher Divergence Critic Regularization

I. Kostrikov, J. Tompson, R. Fergus, O. Nachum

ICML 2021

Image Augmentation is All You Need: Regularizing Deep Reinforcement Learning from Pixels

I. Kostrikov*, D. Yarats*, R. Fergus

ICLR 2021, Spotlight

Imitation Learning via Off-Policy Distribution Matching

I. Kostrikov, O. Nachum, J. Tompson

ICLR 2020

Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning

I. Kostrikov, K. Agrawal, D. Dwibedi, S. Levine, J. Tompson

ICLR 2019

Surface Networks

I. Kostrikov, Z. Jiang, D. Panozzo, D. Zorin, J. Bruna

CVPR 2018, Oral

Implementations

JAXRL: Implementations of Reinforcement Learning algorithms in JAX

PyTorch Implementations of Reinforcement Learning Algorithms

Page updated

Google Sites

Report abuse