Ilya Kostrikov

Most-cited papers

GPT-4o System Card
OpenAI Aaron Hurst, A. Lerer, Adam P. Goucher, Adam Perelman +412 more
20245,262 citations
Semantic Scholar
Offline Reinforcement Learning with Implicit Q-Learning
Ilya Kostrikov, Ashvin Nair, S. Levine
2021International Conference on Learning Representations1,852 citations
Semantic Scholar
Training Diffusion Models with Reinforcement Learning
Kevin Black, Michael Janner, Yilun Du, Ilya Kostrikov +1 more
2023International Conference on Learning Representations1,167 citations Open access
Semantic Scholar
Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
Ilya Kostrikov, D. Yarats, R. Fergus
2020International Conference on Learning Representations983 citations
Semantic Scholar
Improving Sample Efficiency in Model-Free Reinforcement Learning from Images
D. Yarats, Amy Zhang, Ilya Kostrikov, Brandon Amos +2 more
2019AAAI Conference on Artificial Intelligence532 citations Open access
Semantic Scholar
PlaNet - Photo Geolocation with Convolutional Neural Networks
Tobias Weyand, Ilya Kostrikov, J. Philbin
2016European Conference on Computer Vision509 citations Open access
Semantic Scholar
Efficient Online Reinforcement Learning with Offline Data
Philip J. Ball, Laura M. Smith, Ilya Kostrikov, S. Levine
2023International Conference on Machine Learning469 citations Open access
Semantic Scholar
Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play
Sainbayar Sukhbaatar, Ze-Ming Lin, Ilya Kostrikov, Gabriel Synnaeve +2 more
2017International Conference on Learning Representations386 citations
Semantic Scholar
IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies
Philippe Hansen-Estruch, Ilya Kostrikov, Michael Janner, J. Kuba +1 more
2023arXiv.org372 citations Open access
Semantic Scholar
Offline Reinforcement Learning with Fisher Divergence Critic Regularization
Ilya Kostrikov, Jonathan Tompson, R. Fergus, Ofir Nachum
2021International Conference on Machine Learning365 citations
Semantic Scholar
Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning
Ilya Kostrikov, Kumar Krishna Agrawal, Debidatta Dwibedi, S. Levine +1 more
2018302 citations
Semantic Scholar
AlgaeDICE: Policy Gradient from Arbitrary Experience
Ofir Nachum, Bo Dai, Ilya Kostrikov, Yinlam Chow +2 more
2019arXiv.org275 citations
Semantic Scholar
Imitation Learning via Off-Policy Distribution Matching
Ilya Kostrikov, Ofir Nachum, Jonathan Tompson
2019International Conference on Learning Representations261 citations
Semantic Scholar
RvS: What is Essential for Offline RL via Supervised Learning?
Scott Emmons, Benjamin Eysenbach, Ilya Kostrikov, S. Levine
2021International Conference on Learning Representations254 citations
Semantic Scholar
Offline RL for Natural Language Generation with Implicit Language Q Learning
Charles Burton Snell, Ilya Kostrikov, Yi Su, Mengjiao Yang +1 more
2022International Conference on Learning Representations161 citations Open access
Semantic Scholar
A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning
Laura M. Smith, Ilya Kostrikov, Sergey Levine
2022arXiv.org148 citations Open access
Semantic Scholar
Automatic Data Augmentation for Generalization in Reinforcement Learning
R. Raileanu, Maxwell Goldstein, D. Yarats, Ilya Kostrikov +1 more
2021Neural Information Processing Systems144 citations
Semantic Scholar
An Efficient Convolutional Network for Human Pose Estimation
Umer Rafi, B. Leibe, Juergen Gall, Ilya Kostrikov
2016British Machine Vision Conference138 citations
Semantic Scholar
Automatic Data Augmentation for Generalization in Deep Reinforcement Learning
R. Raileanu, Maxwell Goldstein, D. Yarats, Ilya Kostrikov +1 more
2020arXiv.org125 citations
Semantic Scholar
Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning
Ilya Kostrikov, Kumar Krishna Agrawal, Debidatta Dwibedi, S. Levine +1 more
2018International Conference on Learning Representations111 citations
Semantic Scholar
Surface Networks
Ilya Kostrikov, Zhong-Shi Jiang, Daniele Panozzo, D. Zorin +1 more
20172018 IEEE/CVF Conference on Computer Vision and Pattern Recognition108 citations
Semantic Scholar
In Defense of the Unitary Scalarization for Deep Multi-Task Learning
Vitaly Kurin, Alessandro De Palma, Ilya Kostrikov, S. Whiteson +1 more
2022Neural Information Processing Systems98 citations Open access
Semantic Scholar
Depth Sweep Regression Forests for Estimating 3D Human Pose from Images
Ilya Kostrikov, Juergen Gall
2014British Machine Vision Conference88 citations
Semantic Scholar
Demonstrating A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning
Ilya Kostrikov, Laura M. Smith, S. Levine
2023Robotics: Science and Systems Conference57 citations Open access
Semantic Scholar
Efficient Deep Reinforcement Learning Requires Regulating Overfitting
Qi-Yang Li, Aviral Kumar, Ilya Kostrikov, S. Levine
2023International Conference on Learning Representations50 citations Open access
Semantic Scholar
Offline Reinforcement Learning for Visual Navigation
Dhruv Shah, Arjun Bhorkar, Hrish Leen, Ilya Kostrikov +2 more
2022Conference on Robot Learning47 citations Open access
Semantic Scholar
FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing
Kyle Stachowicz, Dhruv Shah, Arjun Bhorkar, Ilya Kostrikov +1 more
2023Conference on Robot Learning39 citations Open access
Semantic Scholar
Probabilistic Labeling Cost for High-Accuracy Multi-view Reconstruction
Ilya Kostrikov, Esther Horbert, B. Leibe
20142014 IEEE Conference on Computer Vision and Pattern Recognition37 citations
Semantic Scholar
Statistical Bootstrapping for Uncertainty Estimation in Off-Policy Evaluation
Ilya Kostrikov, Ofir Nachum
2020arXiv.org34 citations
Semantic Scholar
OpenAI o3-mini System Card
B. Zhang, Eric Mitchell, Hong-Yu Ren, K. Lu +108 more
31 citations
Semantic Scholar
OpenAI GPT-4.5 System Card
A. Paino, A. Kamali, Amin Tootoonchian, Andrew Tulloch +325 more
30 citations
Semantic Scholar
Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions
Bogdan Mazoure, Ilya Kostrikov, Ofir Nachum, Jonathan Tompson
2021Neural Information Processing Systems29 citations Open access
Semantic Scholar
D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning
Rafael Rafailov, K. Hatch, Anikait Singh, Aviral Kumar +8 more
2024RLJ18 citations
Semantic Scholar
Addressing Sample Inefficiency and Reward Bias in Inverse Reinforcement Learning
Ilya Kostrikov, Kumar Krishna Agrawal, S. Levine, Jonathan Tompson
2018arXiv.org13 citations
Semantic Scholar
Improving Sample Efficiency of Imitation and Reinforcement Learning
Ilya Kostrikov
20211 citations
Semantic Scholar
ALGAE: Policy Gradient from Arbitrary Experience
Ofir Nachum, Bo Dai, Ilya Kostrikov, Dale Schuurmans
20191 citations
Semantic Scholar
ICLR 2019 Expert Replay Buffer ActorEnvironment Discriminator Policy Replay Buffer Absorbing State Wrapper s a Critic
Ilya Kostrikov, Kumar Krishna Agrawal, Debidatta Dwibedi, S. Levine +1 more
20190 citations
Semantic Scholar
Supplementary Material for Surface Networks
Ilya Kostrikov, Zhong-Shi Jiang, Daniele Panozzo, D. Zorin +1 more
20180 citations
Semantic Scholar