Aravind Rajeswaran
Artificial Intelligence · 2016–2024
A researcher in the Science corpus: 19 papers; trusts 1,462 researchers and is trusted by 1,015 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 697 citations into it; #1,043 of 36,961 by trust here, #1,631 by citations
- Reinforcement Learning — 485 citations into it; #182 of 2,250 by trust here, #177 by citations
- Computer Vision and Pattern Recognition — 255 citations into it; #6,909 of 21,973 by trust here, #4,485 by citations
- Control and Systems Engineering — 230 citations into it; #1,013 of 8,519 by trust here, #267 by citations
- Management Science and Operations Research — 133 citations into it; #5,172 of 12,201 by trust here, #3,534 by citations
- Computational Theory and Mathematics — 81 citations into it; #3,377 of 12,489 by trust here, #1,195 by citations
- Robotics & Control — 75 citations into it; #357 of 612 by trust here, #442 by citations
- Optimization & Training — 74 citations into it
Whom Aravind Rajeswaran trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Sergey Levine
- Sham M. Kakade
- E. Todorov
- John Schulman
- Pieter Abbeel
- Diederik P. Kingma
- Ronald J. Williams
- Geoffrey E. Hinton
- Richard S. Sutton
- Alex Krizhevsky
Who trusts Aravind Rajeswaran overall
- Sergey Levine
- Vikash Kumar
- Chelsea Finn
- Abhishek Gupta
- Pieter Abbeel
- Igor Mordatch
- Tianhe Yu
- Ofir Nachum
- Han-Jia Ye
- Bo Dai
Papers from Aravind Rajeswaran's perspective
Ordered by how strongly the researchers Aravind Rajeswaran 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- 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
- Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations (2017) — 1,392 citations
- Towards Generalization and Simplicity in Continuous Control (2017) — 294 citations
- Decision Transformer: Reinforcement Learning via Sequence Modeling (2021) — 2,391 citations
- Divide-and-Conquer Reinforcement Learning (2017) — 135 citations
- EPOpt: Learning Robust Neural Network Policies Using Model Ensembles (2016) — 400 citations
- R3M: A Universal Visual Representation for Robot Manipulation (2022) — 933 citations
- MOReL : Model-Based Offline Reinforcement Learning (2020) — 834 citations
- Meta-Learning with Implicit Gradients (2019) — 1,013 citations
- Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost (2018) — 238 citations
- Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines (2018) — 173 citations
- Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control (2018) — 268 citations
- COMBO: Conservative Offline Model-Based Policy Optimization (2021) — 535 citations
- Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation? (2022) — 102 citations
- Offline Reinforcement Learning from Images with Latent Space Models (2020) — 147 citations
- Reinforcement learning for non-prehensile manipulation: Transfer from simulation to physical system (2018) — 66 citations
- Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence? (2023) — 303 citations
- A Game Theoretic Framework for Model Based Reinforcement Learning (2020) — 141 citations
- OpenEQA: Embodied Question Answering in the Era of Foundation Models (2024) — 348 citations
- Online Meta-Learning (2019) — 325 citations