Prati
Ilya Kostrikov
Ilya Kostrikov
OpenAI
Potvrđena adresa e-pošte na openai.com - Početna stranica
Naslov
Citirano
Citirano
Godina
Image augmentation is all you need: Regularizing deep reinforcement learning from pixels
I Kostrikov*, D Yarats*, R Fergus
arXiv preprint arXiv:2004.13649, 2020
4642020
Planet-photo geolocation with convolutional neural networks
T Weyand, I Kostrikov, J Philbin
Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The …, 2016
4492016
Intrinsic motivation and automatic curricula via asymmetric self-play
S Sukhbaatar, Z Lin, I Kostrikov, G Synnaeve, A Szlam, R Fergus
arXiv preprint arXiv:1703.05407, 2017
3612017
Improving sample efficiency in model-free reinforcement learning from images
D Yarats, A Zhang, I Kostrikov, B Amos, J Pineau, R Fergus
Proceedings of the AAAI Conference on Artificial Intelligence 35 (12), 10674 …, 2021
2572021
Discriminator-actor-critic: Addressing sample inefficiency and reward bias in adversarial imitation learning
I Kostrikov, KK Agrawal, D Dwibedi, S Levine, J Tompson
arXiv preprint arXiv:1809.02925, 2018
2282018
Pytorch implementations of reinforcement learning algorithms
I Kostrikov
GitHub repository: https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail, 2018
1962018
Offline reinforcement learning with implicit q-learning
I Kostrikov, A Nair, S Levine
arXiv preprint arXiv:2110.06169, 2021
1952021
Algaedice: Policy gradient from arbitrary experience
O Nachum, B Dai, I Kostrikov, Y Chow, L Li, D Schuurmans
arXiv preprint arXiv:1912.02074, 2019
1532019
An Efficient Convolutional Network for Human Pose Estimation.
U Rafi, B Leibe, J Gall, I Kostrikov
BMVC 1, 2, 2016
1512016
Offline Reinforcement Learning with Fisher Divergence Critic Regularization
I Kostrikov, J Tompson, R Fergus, O Nachum
arXiv preprint arXiv:2103.08050, 2021
1462021
Automatic data augmentation for generalization in deep reinforcement learning
R Raileanu, M Goldstein, D Yarats, I Kostrikov, R Fergus
arXiv preprint arXiv:2006.12862, 2020
123*2020
Imitation learning via off-policy distribution matching
I Kostrikov, O Nachum, J Tompson
arXiv preprint arXiv:1912.05032, 2019
1072019
Depth Sweep Regression Forests for Estimating 3D Human Pose from Images.
I Kostrikov, J Gall
BMVC 1 (2), 5, 2014
952014
Surface networks
I Kostrikov, Z Jiang, D Panozzo, D Zorin, J Bruna
Proceedings of the IEEE conference on computer vision and pattern …, 2018
842018
RvS: What is Essential for Offline RL via Supervised Learning?
S Emmons, B Eysenbach, I Kostrikov, S Levine
arXiv preprint arXiv:2112.10751, 2021
542021
Soft actor-critic (sac) implementation in pytorch
D Yarats, I Kostrikov
412020
Probabilistic labeling cost for high-accuracy multi-view reconstruction
I Kostrikov, E Horbert, B Leibe
Proceedings of the ieee conference on computer vision and pattern …, 2014
262014
A walk in the park: Learning to walk in 20 minutes with model-free reinforcement learning
L Smith*, I Kostrikov*, S Levine
arXiv preprint arXiv:2208.07860, 2022
252022
In defense of the unitary scalarization for deep multi-task learning
V Kurin, A De Palma, I Kostrikov, S Whiteson, PK Mudigonda
Advances in Neural Information Processing Systems 35, 12169-12183, 2022
202022
Statistical bootstrapping for uncertainty estimation in off-policy evaluation
I Kostrikov, O Nachum
arXiv preprint arXiv:2007.13609, 2020
202020
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20