Výsledky vyhledávání

Report

D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning

Autor: Rafailov, Rafael, Hatch, Kyle, Singh, Anikait, Smith, Laura, Kumar, Aviral, Kostrikov, Ilya, Hansen-Estruch, Philippe, Kolev, Victor, Ball, Philip, Wu, Jiajun, Finn, Chelsea, Levine, Sergey

Offline reinforcement learning algorithms hold the promise of enabling data-driven RL methods that do not require costly or dangerous real-world exploration and benefit from large pre-collected datasets. This in turn can facilitate real-world applica

Externí odkaz: http://arxiv.org/abs/2408.08441

Zobrazit plný text záznamu

Report

Video Occupancy Models

Autor: Tomar, Manan, Hansen-Estruch, Philippe, Bachman, Philip, Lamb, Alex, Langford, John, Taylor, Matthew E., Levine, Sergey

We introduce a new family of video prediction models designed to support downstream control tasks. We call these models Video Occupancy models (VOCs). VOCs operate in a compact latent space, thus avoiding the need to make predictions about individual

Externí odkaz: http://arxiv.org/abs/2407.09533

Zobrazit plný text záznamu

Report

Unified Auto-Encoding with Masked Diffusion

Autor: Hansen-Estruch, Philippe, Vishwanath, Sriram, Zhang, Amy, Tomar, Manan

At the core of both successful generative and self-supervised representation learning models there is a reconstruction objective that incorporates some form of image corruption. Diffusion models implement this approach through a scheduled Gaussian co

Externí odkaz: http://arxiv.org/abs/2406.17688

Zobrazit plný text záznamu

Report

BridgeData V2: A Dataset for Robot Learning at Scale

Autor: Walke, Homer, Black, Kevin, Lee, Abraham, Kim, Moo Jin, Du, Max, Zheng, Chongyi, Zhao, Tony, Hansen-Estruch, Philippe, Vuong, Quan, He, Andre, Myers, Vivek, Fang, Kuan, Finn, Chelsea, Levine, Sergey

We introduce BridgeData V2, a large and diverse dataset of robotic manipulation behaviors designed to facilitate research on scalable robot learning. BridgeData V2 contains 60,096 trajectories collected across 24 environments on a publicly available

Externí odkaz: http://arxiv.org/abs/2308.12952

Zobrazit plný text záznamu

Report

Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control

Autor: Myers, Vivek, He, Andre, Fang, Kuan, Walke, Homer, Hansen-Estruch, Philippe, Cheng, Ching-An, Jalobeanu, Mihai, Kolobov, Andrey, Dragan, Anca, Levine, Sergey

Our goal is for robots to follow natural language instructions like "put the towel next to the microwave." But getting large amounts of labeled data, i.e. data that contains demonstrations of tasks labeled with the language instruction, is prohibitiv

Externí odkaz: http://arxiv.org/abs/2307.00117

Zobrazit plný text záznamu

Report

IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies

Autor: Hansen-Estruch, Philippe, Kostrikov, Ilya, Janner, Michael, Kuba, Jakub Grudzien, Levine, Sergey

Effective offline RL methods require properly handling out-of-distribution actions. Implicit Q-learning (IQL) addresses this by training a Q-function using only dataset actions through a modified Bellman backup. However, it is unclear which policy ac

Externí odkaz: http://arxiv.org/abs/2304.10573

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání