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 Kimin Lee

PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training


Jun 09, 2021
Kimin Lee, Laura Smith, Pieter Abbeel

* ICML 2021. First two authors contributed equally. Website: https://sites.google.com/view/icml21pebble Code: https://github.com/pokaxpoka/B_Pref 

  Access Paper or Ask Questions

Decision Transformer: Reinforcement Learning via Sequence Modeling


Jun 02, 2021
Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, Igor Mordatch

* First two authors contributed equally. Last two authors advised equally 

  Access Paper or Ask Questions

Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings


Mar 04, 2021
Lili Chen, Kimin Lee, Aravind Srinivas, Pieter Abbeel


  Access Paper or Ask Questions

State Entropy Maximization with Random Encoders for Efficient Exploration


Feb 18, 2021
Younggyo Seo, Lili Chen, Jinwoo Shin, Honglak Lee, Pieter Abbeel, Kimin Lee

* First two authors contributed equally, website: https://sites.google.com/view/re3-rl 

  Access Paper or Ask Questions

MASKER: Masked Keyword Regularization for Reliable Text Classification


Dec 17, 2020
Seung Jun Moon, Sangwoo Mo, Kimin Lee, Jaeho Lee, Jinwoo Shin

* AAAI 2021. First two authors contributed equally 

  Access Paper or Ask Questions

Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in First-person Simulated 3D Environments


Oct 28, 2020
Wilka Carvalho, Anthony Liang, Kimin Lee, Sungryull Sohn, Honglak Lee, Richard L. Lewis, Satinder Singh


  Access Paper or Ask Questions

Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning


Oct 26, 2020
Younggyo Seo, Kimin Lee, Ignasi Clavera, Thanard Kurutach, Jinwoo Shin, Pieter Abbeel

* Accepted in NeurIPS2020. First two authors contributed equally, website: https://sites.google.com/view/trajectory-mcl code: https://github.com/younggyoseo/trajectory_mcl 

  Access Paper or Ask Questions

Decoupling Representation Learning from Reinforcement Learning


Sep 30, 2020
Adam Stooke, Kimin Lee, Pieter Abbeel, Michael Laskin

* Improved related works and fixed code hyperlink 

  Access Paper or Ask Questions

Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning


Aug 03, 2020
Xingyu Lu, Kimin Lee, Pieter Abbeel, Stas Tiomkin

* 16 pages 

  Access Paper or Ask Questions

Learning to Sample with Local and Global Contexts in Experience Replay Buffer


Jul 14, 2020
Youngmin Oh, Kimin Lee, Jinwoo Shin, Eunho Yang, Sung Ju Hwang


  Access Paper or Ask Questions

SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning


Jul 09, 2020
Kimin Lee, Michael Laskin, Aravind Srinivas, Pieter Abbeel


  Access Paper or Ask Questions

Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning


May 14, 2020
Kimin Lee, Younggyo Seo, Seunghyun Lee, Honglak Lee, Jinwoo Shin

* First two authors contributed equally, website: https://sites.google.com/view/cadm code: https://github.com/younggyoseo/CaDM 

  Access Paper or Ask Questions

Reinforcement Learning with Augmented Data


May 11, 2020
Michael Laskin, Kimin Lee, Adam Stooke, Lerrel Pinto, Pieter Abbeel, Aravind Srinivas

* First two authors contributed equally, website: https://mishalaskin.github.io/rad code: https://github.com/MishaLaskin/rad and https://github.com/pokaxpoka/rad_procgen 

  Access Paper or Ask Questions

Regularizing Class-wise Predictions via Self-knowledge Distillation


Apr 07, 2020
Sukmin Yun, Jongjin Park, Kimin Lee, Jinwoo Shin

* Accepted to CVPR 2020. Code is available at https://github.com/alinlab/cs-kd 

  Access Paper or Ask Questions

A Simple Randomization Technique for Generalization in Deep Reinforcement Learning


Oct 11, 2019
Kimin Lee, Kibok Lee, Jinwoo Shin, Honglak Lee

* In NeurIPS Workshop on Deep RL, 2019 / First two authors are equally contributed 

  Access Paper or Ask Questions

Incremental Learning with Unlabeled Data in the Wild


Mar 29, 2019
Kibok Lee, Kimin Lee, Jinwoo Shin, Honglak Lee


  Access Paper or Ask Questions

Robust Inference via Generative Classifiers for Handling Noisy Labels


Jan 31, 2019
Kimin Lee, Sukmin Yun, Kibok Lee, Honglak Lee, Bo Li, Jinwoo Shin


  Access Paper or Ask Questions

Using Pre-Training Can Improve Model Robustness and Uncertainty


Jan 28, 2019
Dan Hendrycks, Kimin Lee, Mantas Mazeika


  Access Paper or Ask Questions

A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks


Oct 27, 2018
Kimin Lee, Kibok Lee, Honglak Lee, Jinwoo Shin

* Accepted in NIPS 2018 

  Access Paper or Ask Questions

Hierarchical Novelty Detection for Visual Object Recognition


Jun 15, 2018
Kibok Lee, Kimin Lee, Kyle Min, Yuting Zhang, Jinwoo Shin, Honglak Lee

* CVPR 2018 

  Access Paper or Ask Questions

Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples


Feb 23, 2018
Kimin Lee, Honglak Lee, Kibok Lee, Jinwoo Shin


  Access Paper or Ask Questions

Confident Multiple Choice Learning


Sep 22, 2017
Kimin Lee, Changho Hwang, KyoungSoo Park, Jinwoo Shin

* Accepted in ICML 2017 

  Access Paper or Ask Questions

Simplified Stochastic Feedforward Neural Networks


Apr 11, 2017
Kimin Lee, Jaehyung Kim, Song Chong, Jinwoo Shin

* 22 pages, 6 figures 

  Access Paper or Ask Questions