activity
20162023
most citedDecision Transformer: Reinforcement Learning via Sequence Modeling

465 citations · 1.2k across the 32 of their papers we have counts for

collaborators
Showing 2021 · cs.LGShow all

7 papers · 2 filters

cs.LG2021★ 4 cited

BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery

Chris Cundy, Aditya Grover, Stefano Ermon

A structural equation model (SEM) is an effective framework to reason over causal relationships represented via a directed acyclic graph (DAG). Recent advances have enabled effecti…

cs.LG2021★ 10 cited

Frame Averaging for Invariant and Equivariant Network Design

Omri Puny, Matan Atzmon, Heli Ben-Hamu +4

Many machine learning tasks involve learning functions that are known to be invariant or equivariant to certain symmetries of the input data. However, it is often challenging to de…

cs.LG2021★ 465 cited

Decision Transformer: Reinforcement Learning via Sequence Modeling

Lili Chen, Kevin Lu, Aravind Rajeswaran +6

We introduce a framework that abstracts Reinforcement Learning (RL) as a sequence modeling problem. This allows us to draw upon the simplicity and scalability of the Transformer ar…

cs.LG2021★ 51 cited

Rotation Invariant Graph Neural Networks using Spin Convolutions

Muhammed Shuaibi, Adeesh Kolluru, Abhishek Das +4

Progress towards the energy breakthroughs needed to combat climate change can be significantly accelerated through the efficient simulation of atomic systems. Simulation techniques…

cs.LG2021

JUMBO: Scalable Multi-task Bayesian Optimization using Offline Data

Kourosh Hakhamaneshi, Pieter Abbeel, Vladimir Stojanovic +1

The goal of Multi-task Bayesian Optimization (MBO) is to minimize the number of queries required to accurately optimize a target black-box function, given access to offline evaluat…

cs.LG2021

Pretrained Transformers as Universal Computation Engines

Kevin Lu, Aditya Grover, Pieter Abbeel +1

We investigate the capability of a transformer pretrained on natural language to generalize to other modalities with minimal finetuning -- in particular, without finetuning of the…