713 citations · 2.8k across the 24 of their papers we have counts for
28 papers
MemWM: Memory-Augmented Text-Based World Model
Yujun Wang, Tao Zhang, Jinhe Bi +9
World models are increasingly used to support planning in agents by predicting how environment states evolve in response to agent actions. Yet fluent next-state predictions can sti…
Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions
Yevgen Chebotar, Quan Vuong, Alex Irpan +22
In this work, we present a scalable reinforcement learning method for training multi-task policies from large offline datasets that can leverage both human demonstrations and auton…
Deep RL at Scale: Sorting Waste in Office Buildings with a Fleet of Mobile Manipulators
Alexander Herzog, Kanishka Rao, Karol Hausman +37
We describe a system for deep reinforcement learning of robotic manipulation skills applied to a large-scale real-world task: sorting recyclables and trash in office buildings. Rea…
RT-1: Robotics Transformer for Real-World Control at Scale
Anthony Brohan, Noah Brown, Justice Carbajal +48
By transferring knowledge from large, diverse, task-agnostic datasets, modern machine learning models can solve specific downstream tasks either zero-shot or with small task-specif…
Token Turing Machines
Michael S. Ryoo, Keerthana Gopalakrishnan, Kumara Kahatapitiya +6
We propose Token Turing Machines (TTM), a sequential, autoregressive Transformer model with memory for real-world sequential visual understanding. Our model is inspired by the semi…
Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
Michael Ahn, Anthony Brohan, Noah Brown +42
Large language models can encode a wealth of semantic knowledge about the world. Such knowledge could be extremely useful to robots aiming to act upon high-level, temporally extend…
MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance
Michael Luo, Ashwin Balakrishna, Brijen Thananjeyan +6
Safe exploration is critical for using reinforcement learning (RL) in risk-sensitive environments. Recent work learns risk measures which measure the probability of violating const…
Visionary: Vision architecture discovery for robot learning
Iretiayo Akinola, Anelia Angelova, Yao Lu +5
We propose a vision-based architecture search algorithm for robot manipulation learning, which discovers interactions between low dimension action inputs and high dimensional visua…
How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned
Julian Ibarz, Jie Tan, Chelsea Finn +3
Deep reinforcement learning (RL) has emerged as a promising approach for autonomously acquiring complex behaviors from low level sensor observations. Although a large portion of de…
Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones
Brijen Thananjeyan, Ashwin Balakrishna, Suraj Nair +7
Safety remains a central obstacle preventing widespread use of RL in the real world: learning new tasks in uncertain environments requires extensive exploration, but safety require…
RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real
Kanishka Rao, Chris Harris, Alex Irpan +3
Deep neural network based reinforcement learning (RL) can learn appropriate visual representations for complex tasks like vision-based robotic grasping without the need for manuall…
Thinking While Moving: Deep Reinforcement Learning with Concurrent Control
Ted Xiao, Eric Jang, Dmitry Kalashnikov +4
We study reinforcement learning in settings where sampling an action from the policy must be done concurrently with the time evolution of the controlled system, such as when a robo…
Off-Policy Evaluation via Off-Policy Classification
Alex Irpan, Kanishka Rao, Konstantinos Bousmalis +3
In this work, we consider the problem of model selection for deep reinforcement learning (RL) in real-world environments. Typically, the performance of deep RL algorithms is evalua…
Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks
Stephen James, Paul Wohlhart, Mrinal Kalakrishnan +6
Real world data, especially in the domain of robotics, is notoriously costly to collect. One way to circumvent this can be to leverage the power of simulation to produce large amou…
QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
Dmitry Kalashnikov, Alex Irpan, Peter Pastor +8
In this paper, we study the problem of learning vision-based dynamic manipulation skills using a scalable reinforcement learning approach. We study this problem in the context of g…
Large Scale Scene Text Verification with Guided Attention
Dafang He, Yeqing Li, Alexander Gorban +5
Many tasks are related to determining if a particular text string exists in an image. In this work, we propose a new framework that learns this task in an end-to-end way. The frame…
Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods
Deirdre Quillen, Eric Jang, Ofir Nachum +3
In this paper, we explore deep reinforcement learning algorithms for vision-based robotic grasping. Model-free deep reinforcement learning (RL) has been successfully applied to a r…
Diversity is All You Need: Learning Skills without a Reward Function
Benjamin Eysenbach, Abhishek Gupta, Julian Ibarz +1
Intelligent creatures can explore their environments and learn useful skills without supervision. In this paper, we propose DIAYN ('Diversity is All You Need'), a method for learni…
Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning
Benjamin Eysenbach, Shixiang Gu, Julian Ibarz +1
Deep reinforcement learning algorithms can learn complex behavioral skills, but real-world application of these methods requires a large amount of experience to be collected by the…
Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping
Konstantinos Bousmalis, Alex Irpan, Paul Wohlhart +9
Instrumenting and collecting annotated visual grasping datasets to train modern machine learning algorithms can be extremely time-consuming and expensive. An appealing alternative…
End-to-End Learning of Semantic Grasping
Eric Jang, Sudheendra Vijayanarasimhan, Peter Pastor +2
We consider the task of semantic robotic grasping, in which a robot picks up an object of a user-specified class using only monocular images. Inspired by the two-stream hypothesis…
Discrete Sequential Prediction of Continuous Actions for Deep RL
Luke Metz, Julian Ibarz, Navdeep Jaitly +1
It has long been assumed that high dimensional continuous control problems cannot be solved effectively by discretizing individual dimensions of the action space due to the exponen…
In-Datacenter Performance Analysis of a Tensor Processing Unit
Norman P. Jouppi, Cliff Young, Nishant Patil +72
Many architects believe that major improvements in cost-energy-performance must now come from domain-specific hardware. This paper evaluates a custom ASIC---called a Tensor Process…
Attention-based Extraction of Structured Information from Street View Imagery
Zbigniew Wojna, Alex Gorban, Dar-Shyang Lee +4
We present a neural network model - based on CNNs, RNNs and a novel attention mechanism - which achieves 84.2% accuracy on the challenging French Street Name Signs (FSNS) dataset,…