大神 一年100篇论文

https://scholar.google.com/citations?hl=en&user=8R35rCwAAAAJ&view_op=list_works&sortby=pubdate

Sergey Levine

UC Berkeley, Google

Verified email at eecs.berkeley.edu - Homepage

Machine LearningRoboticsReinforcement Learning

TITLE	CITED BY	YEAR
Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL A Nagabandi, C Finn, S Levine arXiv preprint arXiv:1812.07671		2018
Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks S James, P Wohlhart, M Kalakrishnan, D Kalashnikov, A Irpan, J Ibarz, ... arXiv preprint arXiv:1812.07252		2018
Soft Actor-Critic Algorithms and Applications T Haarnoja, A Zhou, K Hartikainen, G Tucker, S Ha, J Tan, V Kumar, ... arXiv preprint arXiv:1812.05905		2018
Residual Reinforcement Learning for Robot Control T Johannink, S Bahl, A Nair, J Luo, A Kumar, M Loskyll, JA Ojea, ... arXiv preprint arXiv:1812.03201	1	2018
SFV: reinforcement learning of physical skills from videos XB Peng, A Kanazawa, J Malik, P Abbeel, S Levine SIGGRAPH Asia 2018 Technical Papers, 178	4	2018
Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control F Ebert, C Finn, S Dasari, A Xie, A Lee, S Levine arXiv preprint arXiv:1812.00568		2018
Hierarchical Policy Design for Sample-Efficient Learning of Robot Table Tennis Through Self-Play R Mahjourian, N Jaitly, N Lazic, S Levine, R Miikkulainen arXiv preprint arXiv:1811.12927		2018
Guiding Policies with Language via Meta-Learning JD Co-Reyes, A Gupta, S Sanjeev, N Altieri, J DeNero, P Abbeel, ... arXiv preprint arXiv:1811.07882		2018
Learning Actionable Representations with Goal-Conditioned Policies D Ghosh, A Gupta, S Levine arXiv preprint arXiv:1811.07819		2018
Grasp2vec: Learning object representations from self-supervised grasping E Jang, C Devin, V Vanhoucke, S Levine arXiv preprint arXiv:1811.06964	2	2018
One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks T Yu, P Abbeel, S Levine, C Finn arXiv preprint arXiv:1810.11043		2018
Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation D Kalashnikov, A Irpan, P Pastor, J Ibarz, A Herzog, E Jang, D Quillen, ... Conference on Robot Learning, 651-673	1	2018
Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation G Kahn, A Villaflor, P Abbeel, S Levine arXiv preprint arXiv:1810.07167		2018
Deep Imitative Models for Flexible Inference, Planning, and Control N Rhinehart, R McAllister, S Levine arXiv preprint arXiv:1810.06544		2018
Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost H Zhu, A Gupta, A Rajeswaran, S Levine, V Kumar arXiv preprint arXiv:1810.06045	2	2018
Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning F Ebert, S Dasari, AX Lee, S Levine, C Finn arXiv preprint arXiv:1810.03043	1	2018
Unsupervised learning via meta-learning K Hsu, S Levine, C Finn arXiv preprint arXiv:1810.02334	2	2018
Near-Optimal Representation Learning for Hierarchical Reinforcement Learning O Nachum, S Gu, H Lee, S Levine arXiv preprint arXiv:1810.01257		2018
EMI: Exploration with Mutual Information Maximizing State and Action Embeddings H Kim, J Kim, Y Jeong, S Levine, HO Song arXiv preprint arXiv:1810.01176		2018
Time Reversal as Self-Supervision S Nair, M Babaeizadeh, C Finn, S Levine, V Kumar arXiv preprint arXiv:1810.01128		2018
Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow XB Peng, A Kanazawa, S Toyer, P Abbeel, S Levine arXiv preprint arXiv:1810.00821	1	2018
Few-Shot Goal Inference for Visuomotor Learning and Planning A Xie, A Singh, S Levine, C Finn arXiv preprint arXiv:1810.00482	2	2018
Reasoning About Physical Interactions with Object-Centric Models M Janner, S Levine, WT Freeman, JB Tenenbaum, C Finn, J Wu		2018
Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning I Kostrikov, KK Agrawal, D Dwibedi, S Levine, J Tompson		2018
Learning to Adapt in Dynamic, Real-World Environments through Meta-Reinforcement Learning I Clavera, A Nagabandi, S Liu, RS Fearing, P Abbeel, S Levine, C Finn		2018
SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning M Zhang, S Vikram, L Smith, P Abbeel, M Johnson, S Levine		2018
Addressing Sample Inefficiency and Reward Bias in Inverse Reinforcement Learning I Kostrikov, KK Agrawal, S Levine, J Tompson arXiv preprint arXiv:1809.02925	1	2018
Solar: Deep structured latent representations for model-based reinforcement learning M Zhang, S Vikram, L Smith, P Abbeel, MJ Johnson, S Levine arXiv preprint arXiv:1808.09105	3	2018
Time-Agnostic Prediction: Predicting Predictable Video Frames D Jayaraman, F Ebert, AA Efros, S Levine arXiv preprint arXiv:1808.07784		2018
Automatically composing representation transformations as a means for generalization MB Chang, A Gupta, S Levine, TL Griffiths arXiv preprint arXiv:1807.04640	2	2018
Universal planning networks: Learning generalizable representations for visuomotor control A Srinivas, A Jabri, P Abbeel, S Levine, C Finn International Conference on Machine Learning, 4739-4748	1	2018
Learning Flexible and Reusable Locomotion Primitives for a Microrobot B Yang, G Wang, R Calandra, D Contreras, S Levine, K Pister IEEE Robotics and Automation Letters 3 (3), 1904-1911	2	2018
Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation D Kalashnikov, A Irpan, P Pastor, J Ibarz, A Herzog, E Jang, D Quillen, ... arXiv preprint arXiv:1806.10293	12	2018
Learning Instance Segmentation by Interaction D Pathak, Y Shentu, D Chen, P Agrawal, T Darrell, S Levine, J Malik Proceedings of the IEEE Conference on Computer Vision and Pattern …	2	2018
Unsupervised Meta-Learning for Reinforcement Learning A Gupta, B Eysenbach, C Finn, S Levine arXiv preprint arXiv:1806.04640	4	2018
Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings JD Co-Reyes, YX Liu, A Gupta, B Eysenbach, P Abbeel, S Levine arXiv preprint arXiv:1806.02813	7	2018
Probabilistic Model-Agnostic Meta-Learning C Finn, K Xu, S Levine arXiv preprint arXiv:1806.02817	15	2018
Deep machine learning methods and apparatus for robotic grasping S Vijayanarasimhan, E Jang, PP Sampedro, S Levine US Patent App. 15/881,189		2018
Learning a Prior over Intent via Meta-Inverse Reinforcement Learning K Xu, E Ratner, A Dragan, S Levine, C Finn arXiv preprint arXiv:1805.12573	2	2018
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models K Chua, R Calandra, R McAllister, S Levine arXiv preprint arXiv:1805.12114	11	2018
Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition J Fu, A Singh, D Ghosh, L Yang, S Levine arXiv preprint arXiv:1805.11686	2	2018
More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch R Calandra, A Owens, D Jayaraman, J Lin, W Yuan, J Malik, EH Adelson, ... arXiv preprint arXiv:1805.11085	6	2018
Few-Shot Segmentation Propagation with Guided Networks K Rakelly, E Shelhamer, T Darrell, AA Efros, S Levine arXiv preprint arXiv:1806.07373	1	2018
Where Do You Think You're Going?: Inferring Beliefs about Dynamics from Behavior S Reddy, AD Dragan, S Levine arXiv preprint arXiv:1805.08010		2018
Data-Efficient Hierarchical Reinforcement Learning O Nachum, S Gu, H Lee, S Levine arXiv preprint arXiv:1805.08296	13	2018
Time-contrastive networks: Self-supervised learning from video P Sermanet, C Lynch, Y Chebotar, J Hsu, E Jang, S Schaal, S Levine, ... 2018 IEEE International Conference on Robotics and Automation (ICRA), 1134-1141	57	2018
Self-supervised deep reinforcement learning with generalized computation graphs for robot navigation G Kahn, A Villaflor, B Ding, P Abbeel, S Levine 2018 IEEE International Conference on Robotics and Automation (ICRA), 1-8	22	2018
Using simulation and domain adaptation to improve efficiency of deep robotic grasping K Bousmalis, A Irpan, P Wohlhart, Y Bai, M Kelcey, M Kalakrishnan, ... 2018 IEEE International Conference on Robotics and Automation (ICRA), 4243-4250	64	2018
Deep object-centric representations for generalizable robot learning C Devin, P Abbeel, T Darrell, S Levine 2018 IEEE International Conference on Robotics and Automation (ICRA), 7111-7118	7	2018
Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning A Nagabandi, G Kahn, RS Fearing, S Levine 2018 IEEE International Conference on Robotics and Automation (ICRA), 7559-7566	56	2018
Vision-based multi-task manipulation for inexpensive robots using end-to-end learning from demonstration R Rahmatizadeh, P Abolghasemi, L Bölöni, S Levine 2018 IEEE International Conference on Robotics and Automation (ICRA), 3758-3765	18	2018
Imitation from observation: Learning to imitate behaviors from raw video via context translation YX Liu, A Gupta, P Abbeel, S Levine 2018 IEEE International Conference on Robotics and Automation (ICRA), 1118-1125	36	2018
Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review S Levine arXiv preprint arXiv:1805.00909	12	2018
Latent Space Policies for Hierarchical Reinforcement Learning T Haarnoja, K Hartikainen, P Abbeel, S Levine arXiv preprint arXiv:1804.02808	9	2018
DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills XB Peng, P Abbeel, S Levine, M van de Panne arXiv preprint arXiv:1804.02717	39	2018
Stochastic Adversarial Video Prediction AX Lee, R Zhang, F Ebert, P Abbeel, C Finn, S Levine arXiv preprint arXiv:1804.01523	21	2018
Universal Planning Networks A Srinivas, A Jabri, P Abbeel, S Levine, C Finn arXiv preprint arXiv:1804.00645	19	2018
Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments Ł Kidziński, SP Mohanty, C Ong, Z Huang, S Zhou, A Pechenko, ... arXiv preprint arXiv:1804.00361	3	2018
Recall Traces: Backtracking Models for Efficient Reinforcement Learning A Goyal, P Brakel, W Fedus, T Lillicrap, S Levine, H Larochelle, Y Bengio arXiv preprint arXiv:1804.00379	6	2018
Learning to Run challenge: Synthesizing physiologically accurate motion using deep reinforcement learning Ł Kidziński, SP Mohanty, C Ong, JL Hicks, SF Carroll, S Levine, M Salathé, ... arXiv preprint arXiv:1804.00198	4	2018
Learning to Adapt: Meta-Learning for Model-Based Control I Clavera, A Nagabandi, RS Fearing, P Abbeel, S Levine, C Finn arXiv preprint arXiv:1803.11347	12	2018
Composable Deep Reinforcement Learning for Robotic Manipulation T Haarnoja, V Pong, A Zhou, M Dalal, P Abbeel, S Levine arXiv preprint arXiv:1803.06773	16	2018
Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods D Quillen, E Jang, O Nachum, C Finn, J Ibarz, S Levine arXiv preprint arXiv:1802.10264	8	2018
Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning V Feinberg, A Wan, I Stoica, MI Jordan, JE Gonzalez, S Levine arXiv preprint arXiv:1803.00101	9	2018
The mirage of action-dependent baselines in reinforcement learning G Tucker, S Bhupatiraju, S Gu, RE Turner, Z Ghahramani, S Levine arXiv preprint arXiv:1802.10031	12	2018
Temporal difference models: Model-free deep rl for model-based control V Pong, S Gu, M Dalal, S Levine arXiv preprint arXiv:1802.09081	25	2018
Meta-Reinforcement Learning of Structured Exploration Strategies A Gupta, R Mendonca, YX Liu, P Abbeel, S Levine arXiv preprint arXiv:1802.07245	8	2018
Diversity is All You Need: Learning Skills without a Reward Function B Eysenbach, A Gupta, J Ibarz, S Levine arXiv preprint arXiv:1802.06070	21	2018
Self-Supervised Learning of Object Motion Through Adversarial Video Prediction AX Lee, F Ebert, R Zhang, C Finn, P Abbeel, S Levine		2018
Reinforcement learning from imperfect demonstrations Y Gao, J Lin, F Yu, S Levine, T Darrell arXiv preprint arXiv:1802.05313	14	2018
Conditional Networks for Few-Shot Semantic Segmentation K Rakelly, E Shelhamer, T Darrell, A Efros, S Levine	4	2018
Shared Autonomy via Deep Reinforcement Learning S Reddy, S Levine, A Dragan arXiv preprint arXiv:1802.01744	5	2018
One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning T Yu, C Finn, A Xie, S Dasari, T Zhang, P Abbeel, S Levine arXiv preprint arXiv:1802.01557	30	2018
Recasting gradient-based meta-learning as hierarchical bayes E Grant, C Finn, S Levine, T Darrell, T Griffiths arXiv preprint arXiv:1801.08930	30	2018
Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor T Haarnoja, A Zhou, P Abbeel, S Levine arXiv preprint arXiv:1801.01290	45	2018
Visual Memory for Robust Path Following A Kumar, S Gupta, D Fouhey, S Levine, J Malik Advances in Neural Information Processing Systems, 773-782		2018
Introduction to NIPS 2017 Competition Track S Escalera, M Weimer, M Burtsev, V Malykh, V Logacheva, R Lowe, ... The NIPS'17 Competition: Building Intelligent Systems, 1-23		2018
Visual reinforcement learning with imagined goals AV Nair, V Pong, M Dalal, S Bahl, S Lin, S Levine Advances in Neural Information Processing Systems, 9208-9219	4	2018
Sim2Real Viewpoint Invariant Visual Servoing by Recurrent Control F Sadeghi, A Toshev, E Jang, S Levine Proceedings of the IEEE Conference on Computer Vision and Pattern …	1	2018
Temporal Difference Model Learning: Model-Free Deep RL for Model-Based Control S Levine, S Gu, V Pong		2018
Unifying map and landmark based representations for visual navigation S Gupta, D Fouhey, S Levine, J Malik arXiv preprint arXiv:1712.08125	15	2017
Sim2real view invariant visual servoing by recurrent control F Sadeghi, A Toshev, E Jang, S Levine arXiv preprint arXiv:1712.07642	9	2017
Divide-and-conquer reinforcement learning D Ghosh, A Singh, A Rajeswaran, V Kumar, S Levine arXiv preprint arXiv:1711.09874	7	2017
Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning B Eysenbach, S Gu, J Ibarz, S Levine arXiv preprint arXiv:1711.06782	4	2017
Learning image-conditioned dynamics models for control of under-actuated legged millirobots A Nagabandi, G Yang, T Asmar, R Pandya, G Kahn, S Levine, RS Fearing arXiv preprint arXiv:1711.05253	4	2017
Learning with latent language J Andreas, D Klein, S Levine arXiv preprint arXiv:1711.00482	3	2017
Regret Minimization for Partially Observable Deep Reinforcement Learning PH Jin, S Levine, K Keutzer arXiv preprint arXiv:1710.11424	5	2017
Meta-learning and universality: Deep representations and gradient descent can approximate any learning algorithm C Finn, S Levine arXiv preprint arXiv:1710.11622	20	2017
Stochastic variational video prediction M Babaeizadeh, C Finn, D Erhan, RH Campbell, S Levine arXiv preprint arXiv:1710.11252	37	2017
Learning Robust Rewards with Adversarial Inverse Reinforcement Learning J Fu, K Luo, S Levine arXiv preprint arXiv:1710.11248	26	2017
Gplac: Generalizing vision-based robotic skills using weakly labeled images A Singh, L Yang, S Levine Computer Vision (ICCV), 2017 IEEE International Conference on, 5852-5861	8	2017
The feeling of success: Does touch sensing help predict grasp outcomes? R Calandra, A Owens, M Upadhyaya, W Yuan, J Lin, EH Adelson, ... arXiv preprint arXiv:1710.05512	20	2017
Self-supervised visual planning with temporal skip connections F Ebert, C Finn, AX Lee, S Levine arXiv preprint arXiv:1710.05268	27	2017
Learning complex dexterous manipulation with deep reinforcement learning and demonstrations A Rajeswaran, V Kumar, A Gupta, G Vezzani, J Schulman, E Todorov, ... arXiv preprint arXiv:1709.10087	31	2017
Collective robot reinforcement learning with distributed asynchronous guided policy search A Yahya, A Li, M Kalakrishnan, Y Chebotar, S Levine Intelligent Robots and Systems (IROS), 2017 IEEE/RSJ International …	35	2017
One-shot visual imitation learning via meta-learning C Finn, T Yu, T Zhang, P Abbeel, S Levine arXiv preprint arXiv:1709.04905	58	2017
Mbmf: Model-based priors for model-free reinforcement learning S Bansal, R Calandra, K Chua, S Levine, C Tomlin arXiv preprint arXiv:1709.03153	7	2017
Learning robotic manipulation of granular media C Schenck, J Tompson, D Fox, S Levine arXiv preprint arXiv:1709.02833	2	2017
Deep machine learning methods and apparatus for robotic grasping S Vijayanarasimhan, E Jang, PP Sampedro, S Levine US Patent App. 15/448,013		2017
Deep machine learning methods and apparatus for robotic grasping S Levine, PP Sampedro, A Krizhevsky US Patent App. 15/377,280	3	2017

Articles 1–100

SHOW MORE