activity
20122023
most citedDecision Transformer: Reinforcement Learning via Sequence Modeling

465 citations · 4.4k across the 130 of their papers we have counts for

collaborators
Showing 2020Show all

29 papers · 1 filter

cs.LG2020

Parallel Training of Deep Networks with Local Updates

Michael Laskin, Luke Metz, Seth Nabarro +5

Deep learning models trained on large data sets have been widely successful in both vision and language domains. As state-of-the-art deep learning architectures have continued to g…

cs.LG2020

Reset-Free Lifelong Learning with Skill-Space Planning

Kevin Lu, Aditya Grover, Pieter Abbeel +1

The objective of lifelong reinforcement learning (RL) is to optimize agents which can continuously adapt and interact in changing environments. However, current RL approaches fail…

cs.LG2020★ 7 cited

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

Younggyo Seo, Kimin Lee, Ignasi Clavera +3

Model-based reinforcement learning (RL) has shown great potential in various control tasks in terms of both sample-efficiency and final performance. However, learning a generalizab…

cs.RO2020

LaND: Learning to Navigate from Disengagements

Gregory Kahn, Pieter Abbeel, Sergey Levine

Consistently testing autonomous mobile robots in real world scenarios is a necessary aspect of developing autonomous navigation systems. Each time the human safety monitor disengag…

cs.LG2020★ 13 cited

Robust Reinforcement Learning using Adversarial Populations

Eugene Vinitsky, Yuqing Du, Kanaad Parvate +3

Reinforcement Learning (RL) is an effective tool for controller design but can struggle with issues of robustness, failing catastrophically when the underlying system dynamics are…

cs.RO2020★ 22 cited

Visual Imitation Made Easy

Sarah Young, Dhiraj Gandhi, Shubham Tulsiani +3

Visual imitation learning provides a framework for learning complex manipulation behaviors by leveraging human demonstrations. However, current interfaces for imitation such as kin…