Aviral Kumar
Artificial Intelligence · 16 papers · 2018–2023
A researcher in the Science corpus: 16 papers; trusts 1,380 researchers and is trusted by 1,262 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 649 citations into it; #867 of 36,961 by trust here, #2,028 by citations
- Reinforcement Learning — 583 citations into it; #113 of 2,250 by trust here, #175 by citations
- Control and Systems Engineering — 203 citations into it; #1,472 of 8,519 by trust here, #1,112 by citations
- Management Science and Operations Research — 195 citations into it; #1,883 of 12,201 by trust here, #1,241 by citations
- Computer Vision and Pattern Recognition — 143 citations into it
- Computational Theory and Mathematics — 72 citations into it; #744 of 12,489 by trust here, #510 by citations
- Electrical and Electronic Engineering — 59 citations into it; #1,197 of 16,595 by trust here, #3,654 by citations
- Optimization & Training — 59 citations into it; #2,460 of 2,605 by trust here, #2,316 by citations
Whom Aviral Kumar trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Sergey Levine
- Richard S. Sutton
- Geoffrey E. Hinton
- Diederik P. Kingma
- R´emi Munos
- Alex Krizhevsky
- Yoshua Bengio
- Pieter Abbeel
- Kaiming He
- John Schulman
Who trusts Aviral Kumar overall
- Sergey Levine
- Michael Janner
- Ilya Kostrikov
- Ofir Nachum
- Tianhe Yu
- Shixiang Shane Gu
- Scott Fujimoto
- Anurag Ajay
- Justin Fu
- George Tucker
Papers from Aviral Kumar's perspective
Ordered by how strongly the researchers Aviral Kumar trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Learning Multiple Layers of Features from Tiny Images
Their papers
- D4RL: Datasets for Deep Data-Driven Reinforcement Learning (2020) — 1,854 citations
- Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems (2020) — 2,718 citations
- Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction (2019) — 1,322 citations
- Conservative Q-Learning for Offline Reinforcement Learning (2020) — 2,669 citations
- Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning (2019) — 869 citations
- Diagnosing Bottlenecks in Deep Q-learning Algorithms (2019) — 153 citations
- Reward-Conditioned Policies (2019) — 117 citations
- Benchmarks for Deep Off-Policy Evaluation (2021) — 117 citations
- COMBO: Conservative Offline Model-Based Policy Optimization (2021) — 535 citations
- DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction (2020) — 122 citations
- OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning (2020) — 195 citations
- Graph Normalizing Flows (2019) — 187 citations
- Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models (2023) — 318 citations
- COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning (2020) — 116 citations
- Datasets for Data-Driven Reinforcement Learning (2020) — 5 citations
- Trainable Calibration Measures For Neural Networks From Kernel Mean Embeddings (2018) — 344 citations