research
∙
09/18/2023
Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions
In this work, we present a scalable reinforcement learning method for tr...
share
research
∙
09/07/2023
Bootstrapping Adaptive Human-Machine Interfaces with Offline Reinforcement Learning
Adaptive interfaces can help users perform sequential decision-making ta...
research
∙
08/24/2023
BridgeData V2: A Dataset for Robot Learning at Scale
We introduce BridgeData V2, a large and diverse dataset of robotic manip...
research
∙
07/28/2023
RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
We study how vision-language models trained on Internet-scale data can b...
research
∙
07/24/2023
Contrastive Example-Based Control
While many real-world problems that might benefit from reinforcement lea...
research
∙
07/24/2023
A Connection between One-Step Regularization and Critic Regularization in Reinforcement Learning
As with any machine learning problem with limited data, effective offlin...
research
∙
07/22/2023
HIQL: Offline Goal-Conditioned RL with Latent States as Actions
Unsupervised pre-training has recently become the bedrock for computer v...
research
∙
07/18/2023
Multi-Stage Cable Routing through Hierarchical Imitation Learning
We study the problem of learning to perform multi-stage robotic manipula...
research
∙
06/30/2023
Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control
Our goal is for robots to follow natural language instructions like "put...
research
∙
06/26/2023
ViNT: A Foundation Model for Visual Navigation
General-purpose pre-trained models ("foundation models") have enabled pr...
research
∙
06/19/2023
Confidence-Based Model Selection: When to Take Shortcuts for Subpopulation Shifts
Effective machine learning models learn both robust features that direct...
research
∙
06/06/2023
Stabilizing Contrastive RL: Techniques for Offline Goal Reaching
In the same way that the computer vision (CV) and natural language proce...
research
∙
06/02/2023
SACSoN: Scalable Autonomous Data Collection for Social Navigation
Machine learning provides a powerful tool for building socially complian...
research
∙
05/25/2023
The False Promise of Imitating Proprietary LLMs
An emerging method to cheaply improve a weaker language model is to fine...
research
∙
05/22/2023
Training Diffusion Models with Reinforcement Learning
Diffusion models are a class of flexible generative models trained with ...
research
∙
05/05/2023
Deep RL at Scale: Sorting Waste in Office Buildings with a Fleet of Mobile Manipulators
We describe a system for deep reinforcement learning of robotic manipula...
research
∙
04/20/2023
IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies
Effective offline RL methods require properly handling out-of-distributi...
research
∙
04/20/2023
Efficient Deep Reinforcement Learning Requires Regulating Overfitting
Deep reinforcement learning algorithms that learn policies by trial-and-...
research
∙
04/19/2023
FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing
We present a system that enables an autonomous small-scale RC car to dri...
research
∙
04/10/2023
Reinforcement Learning from Passive Data via Latent Intentions
Passive observational data, such as human videos, is abundant and rich i...
research
∙
03/20/2023
Neural Constraint Satisfaction: Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement
Object rearrangement is a challenge for embodied agents because solving ...
research
∙
03/10/2023
Ignorance is Bliss: Robust Control via Information Gating
Informational parsimony – i.e., using the minimal information required f...
research
∙
03/09/2023
Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning
A compelling use case of offline reinforcement learning (RL) is to obtai...
research
∙
03/06/2023
PaLM-E: An Embodied Multimodal Language Model
Large language models excel at a wide range of complex tasks. However, e...
research
∙
03/03/2023
Learning to Influence Human Behavior with Offline Reinforcement Learning
In the real world, some of the most complex settings for learned agents ...
research
∙
03/01/2023
Grounded Decoding: Guiding Text Generation with Grounded Models for Robot Control
Recent progress in large language models (LLMs) has demonstrated the abi...
research
∙
02/19/2023
Robust and Versatile Bipedal Jumping Control through Multi-Task Reinforcement Learning
This work aims to push the limits of agility for bipedal robots by enabl...
research
∙
02/10/2023
Project and Probe: Sample-Efficient Domain Adaptation by Interpolating Orthogonal Features
Conventional approaches to robustness try to learn a model based on caus...
research
∙
02/08/2023
Predictable MDP Abstraction for Unsupervised Model-Based RL
A key component of model-based reinforcement learning (RL) is a dynamics...
research
∙
02/06/2023
Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts
Training machine learning models robust to distribution shifts is critic...
research
∙
12/24/2022
Understanding the Complexity Gains of Single-Task RL with a Curriculum
Reinforcement learning (RL) problems can be challenging without well-sha...
research
∙
12/21/2022
Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios
Imitation learning (IL) is a simple and powerful way to use high-quality...
research
∙
12/16/2022
Offline Reinforcement Learning for Visual Navigation
Reinforcement learning can enable robots to navigate to distant goals wh...
research
∙
12/13/2022
RT-1: Robotics Transformer for Real-World Control at Scale
By transferring knowledge from large, diverse, task-agnostic datasets, m...
research
∙
12/13/2022
Learning Robotic Navigation from Experience: Principles, Methods, and Recent Results
Navigation is one of the most heavily studied problems in robotics, and ...
research
∙
12/08/2022
Confidence-Conditioned Value Functions for Offline Reinforcement Learning
Offline reinforcement learning (RL) promises the ability to learn effect...
research
∙
12/01/2022
Multi-Task Imitation Learning for Linear Dynamical Systems
We study representation learning for efficient imitation learning over l...
research
∙
11/28/2022
Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes
The potential of offline reinforcement learning (RL) is that high-capaci...
research
∙
11/21/2022
Robotic Skill Acquisition via Instruction Augmentation with Vision-Language Models
In recent years, much progress has been made in learning robotic manipul...
research
∙
11/21/2022
Data-Driven Offline Decision-Making via Invariant Representation Learning
The goal in offline data-driven decision-making is synthesize decisions ...
research
∙
11/02/2022
Dual Generator Offline Reinforcement Learning
In offline RL, constraining the learned policy to remain close to the da...
research
∙
11/02/2022
Offline RL With Realistic Datasets: Heteroskedasticity and Support Constraints
Offline reinforcement learning (RL) learns policies entirely from static...
research
∙
11/01/2022
Adversarial Policies Beat Professional-Level Go AIs
We attack the state-of-the-art Go-playing AI system, KataGo, by training...
research
∙
10/27/2022
Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from Vision
Learning-based methods in robotics hold the promise of generalization, b...
research
∙
10/24/2022
FCM: Forgetful Causal Masking Makes Causal Language Models Better Zero-Shot Learners
Large language models (LLM) trained using the next-token-prediction obje...
research
∙
10/18/2022
Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity
Reinforcement learning provides an automated framework for learning beha...
research
∙
10/17/2022
You Only Live Once: Single-Life Reinforcement Learning
Reinforcement learning algorithms are typically designed to learn a perf...
research
∙
10/14/2022
ExAug: Robot-Conditioned Navigation Policies via Geometric Experience Augmentation
Machine learning techniques rely on large and diverse datasets for gener...
research
∙
10/12/2022
Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Tasks
The utilization of broad datasets has proven to be crucial for generaliz...
research
∙
10/11/2022
