Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Sergey Levine

Sergey Levine

Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control



Katie Kang , Paula Gradu , Jason Choi , Michael Janner , Claire Tomlin , Sergey Levine

Figure 1 for Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control
Figure 2 for Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control
Figure 3 for Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control
Figure 4 for Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control

   Access Paper or Ask Questions

Contrastive Learning as Goal-Conditioned Reinforcement Learning



Benjamin Eysenbach , Tianjun Zhang , Ruslan Salakhutdinov , Sergey Levine

Figure 1 for Contrastive Learning as Goal-Conditioned Reinforcement Learning
Figure 2 for Contrastive Learning as Goal-Conditioned Reinforcement Learning
Figure 3 for Contrastive Learning as Goal-Conditioned Reinforcement Learning
Figure 4 for Contrastive Learning as Goal-Conditioned Reinforcement Learning
* Code is available on the website: https://ben-eysenbach.github.io/contrastive_rl 
   Access Paper or Ask Questions

Imitating Past Successes can be Very Suboptimal



Benjamin Eysenbach , Soumith Udatha , Sergey Levine , Ruslan Salakhutdinov

Figure 1 for Imitating Past Successes can be Very Suboptimal
Figure 2 for Imitating Past Successes can be Very Suboptimal
Figure 3 for Imitating Past Successes can be Very Suboptimal
Figure 4 for Imitating Past Successes can be Very Suboptimal

   Access Paper or Ask Questions

Adversarial Unlearning: Reducing Confidence Along Adversarial Directions



Amrith Setlur , Benjamin Eysenbach , Virginia Smith , Sergey Levine

Figure 1 for Adversarial Unlearning: Reducing Confidence Along Adversarial Directions
Figure 2 for Adversarial Unlearning: Reducing Confidence Along Adversarial Directions
Figure 3 for Adversarial Unlearning: Reducing Confidence Along Adversarial Directions
Figure 4 for Adversarial Unlearning: Reducing Confidence Along Adversarial Directions

   Access Paper or Ask Questions

Multimodal Masked Autoencoders Learn Transferable Representations



Xinyang Geng , Hao Liu , Lisa Lee , Dale Schuurmans , Sergey Levine , Pieter Abbeel

Figure 1 for Multimodal Masked Autoencoders Learn Transferable Representations
Figure 2 for Multimodal Masked Autoencoders Learn Transferable Representations
Figure 3 for Multimodal Masked Autoencoders Learn Transferable Representations
Figure 4 for Multimodal Masked Autoencoders Learn Transferable Representations

   Access Paper or Ask Questions

First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization



Siddharth Reddy , Sergey Levine , Anca D. Dragan

Figure 1 for First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization
Figure 2 for First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization
Figure 3 for First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization
Figure 4 for First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization

   Access Paper or Ask Questions

Planning with Diffusion for Flexible Behavior Synthesis



Michael Janner , Yilun Du , Joshua B. Tenenbaum , Sergey Levine

Figure 1 for Planning with Diffusion for Flexible Behavior Synthesis
Figure 2 for Planning with Diffusion for Flexible Behavior Synthesis
Figure 3 for Planning with Diffusion for Flexible Behavior Synthesis
Figure 4 for Planning with Diffusion for Flexible Behavior Synthesis
* ICML 2022 (long talk). Project page and code at https://diffusion-planning.github.io/ 
   Access Paper or Ask Questions

Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space



Kuan Fang , Patrick Yin , Ashvin Nair , Sergey Levine

Figure 1 for Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space
Figure 2 for Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space
Figure 3 for Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space
Figure 4 for Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space

   Access Paper or Ask Questions

ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters



Xue Bin Peng , Yunrong Guo , Lina Halper , Sergey Levine , Sanja Fidler

Figure 1 for ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters
Figure 2 for ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters
Figure 3 for ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters
Figure 4 for ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters

   Access Paper or Ask Questions

Control-Aware Prediction Objectives for Autonomous Driving



Rowan McAllister , Blake Wulfe , Jean Mercat , Logan Ellis , Sergey Levine , Adrien Gaidon

Figure 1 for Control-Aware Prediction Objectives for Autonomous Driving
Figure 2 for Control-Aware Prediction Objectives for Autonomous Driving
Figure 3 for Control-Aware Prediction Objectives for Autonomous Driving
Figure 4 for Control-Aware Prediction Objectives for Autonomous Driving
* Accepted at IEEE International Conference on Robotics and Automation (ICRA) 2022 
   Access Paper or Ask Questions
1
2
3
4
5
6
7
>>