activity
20172022
most citedOffline Reinforcement Learning with Implicit Q-Learning

131 citations · 151 across the 5 of their papers we have counts for

collaborators

12 papers

cs.LG20225 cited

Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning

Philippe Hansen-Estruch, Amy Zhang, Ashvin Nair +2

Building generalizable goal-conditioned agents from rich observations is a key to reinforcement learning (RL) solving real world problems. Traditionally in goal-conditioned RL, an…

cs.LG2021131 cited

Offline Reinforcement Learning with Implicit Q-Learning

Ilya Kostrikov, Ashvin Nair, Sergey Levine

Offline reinforcement learning requires reconciling two conflicting aims: learning a policy that improves over the behavior policy that collected the dataset, while at the same tim…

cs.RO2021

What Can I Do Here? Learning New Skills by Imagining Visual Affordances

Alexander Khazatsky, Ashvin Nair, Daniel Jing +1

A generalist robot equipped with learned skills must be able to perform many tasks in many different environments. However, zero-shot generalization to new settings is not always p…

cs.LG2021

DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies

Soroush Nasiriany, Vitchyr H. Pong, Ashvin Nair +3

Can we use reinforcement learning to learn general-purpose policies that can perform a wide range of different tasks, resulting in flexible and reusable skills? Contextual policies…

cs.LG2020

AWAC: Accelerating Online Reinforcement Learning with Offline Datasets

Ashvin Nair, Abhishek Gupta, Murtaza Dalal +1

Reinforcement learning (RL) provides an appealing formalism for learning control policies from experience. However, the classic active formulation of RL necessitates a lengthy acti…

cs.LG2020

Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks

Gerrit Schoettler, Ashvin Nair, Juan Aparicio Ojea +2

Robotic insertion tasks are characterized by contact and friction mechanics, making them challenging for conventional feedback control methods due to unmodeled physical effects. Re…