Mrinal Kalakrishnan
Artificial Intelligence · 2008–2024
A researcher in the Science corpus: 20 papers; trusts 922 researchers and is trusted by 138 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 399 citations into it; #5,069 of 36,961 by trust here, #4,056 by citations
- Reinforcement Learning — 260 citations into it; #449 of 2,250 by trust here, #286 by citations
- Control and Systems Engineering — 252 citations into it; #227 of 8,519 by trust here, #63 by citations
- Computer Vision and Pattern Recognition — 225 citations into it; #4,114 of 21,973 by trust here, #2,265 by citations
- Robotics & Control — 110 citations into it; #138 of 612 by trust here, #68 by citations
- Biomedical Engineering — 107 citations into it; #808 of 10,753 by trust here, #902 by citations
- Aerospace Engineering — 54 citations into it
- Representation & Self-Supervised Learning — 46 citations into it
Whom Mrinal Kalakrishnan trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Sergey Levine
- Stefan Schaal
- Jan Peters
- Evangelos A. Theodorou
- Geoffrey E. Hinton
- Andrew Y. Ng
- Pieter Abbeel
- Alex Krizhevsky
- Richard S. Sutton
- Diederik P. Kingma
Who trusts Mrinal Kalakrishnan overall
- Sergey Levine
- Pieter Abbeel
- Chelsea Finn
- Anca Dragan
- Harish Chaandar Ravichandar
- Péter Englert
- Peter Pastor
- Ahmed Hussain Qureshi
- Abhishek Gupta
- Yevgen Chebotar
Papers from Mrinal Kalakrishnan's perspective
Ordered by how strongly the researchers Mrinal Kalakrishnan trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Attention is All you Need (Neural Information Processing Systems)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- GENERATIVE ADVERSARIAL NETS
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation (2018) — 1,735 citations
- Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping (2018) — 731 citations
- Path integral guided policy search (2016) — 157 citations
- Collective robot reinforcement learning with distributed asynchronous guided policy search (2016) — 163 citations
- Skill learning and task outcome prediction for manipulation (2011) — 235 citations
- Learning objective functions for manipulation (2013) — 156 citations
- Sim-To-Real via Sim-To-Sim: Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation Networks (2018) — 508 citations
- STOMP: Stochastic trajectory optimization for motion planning (2011) — 1,015 citations
- Learning locomotion over rough terrain using terrain templates (2009) — 106 citations
- Multi-Task Domain Adaptation for Deep Learning of Instance Grasping from Simulation (2017) — 129 citations
- Watch, Try, Learn: Meta-Learning from Demonstrations and Reward (2019) — 54 citations
- OpenEQA: Embodied Question Answering in the Era of Foundation Models (2024) — 348 citations
- Quantile QT-Opt for Risk-Aware Vision-Based Robotic Grasping (2019) — 60 citations
- How to train your robot with deep reinforcement learning: lessons we have learned (2021) — 684 citations
- Learning force control policies for compliant manipulation (2011) — 176 citations
- Learning of grasp selection based on shape-templates (2013) — 134 citations
- Action Image Representation: Learning Scalable Deep Grasping Policies with Zero Real World Data (2020) — 26 citations
- Learning motion primitive goals for robust manipulation (2011) — 49 citations
- Learning, planning, and control for quadruped locomotion over challenging terrain (2011) — 342 citations
- Proc. Advances in Neural Information Processing Systems (NIPS '08) (2008) — 6 citations