Search Results - "Szot, Andrew"

Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second by Berges, Vincent-Pierre, Szot, Andrew, Chaplot, Devendra Singh, Gokaslan, Aaron, Mottaghi, Roozbeh, Batra, Dhruv, Undersander, Eric

“…We present Galactic, a large-scale simulation and reinforcement-learning (RL) framework for robotic mobile manipulation in indoor environments. Specifically, a…”
Get full text

Skill Transformer: A Monolithic Policy for Mobile Manipulation by Huang, Xiaoyu, Batra, Dhruv, Rai, Akshara, Szot, Andrew

“…We present Skill Transformer, an approach for solving long-horizon robotic tasks by combining conditional sequence modeling and skill modularity. Conditioned…”
Get full text

BC-IRL: Learning Generalizable Reward Functions from Demonstrations by Szot, Andrew, Zhang, Amy, Batra, Dhruv, Kira, Zsolt, Meier, Franziska

“…How well do reward functions learned with inverse reinforcement learning (IRL) generalize? We illustrate that state-of-the-art IRL algorithms, which maximize a…”
Get full text

ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI by Elawady, Ahmad, Chhablani, Gunjan, Ramrakhya, Ram, Yadav, Karmesh, Batra, Dhruv, Kira, Zsolt, Szot, Andrew

“…Intelligent embodied agents need to quickly adapt to new scenarios by integrating long histories of experience into decision-making. For instance, a robot in…”
Get full text

Reinforcement Learning via Auxiliary Task Distillation by Harish, Abhinav Narayan, Heck, Larry, Hanna, Josiah P, Kira, Zsolt, Szot, Andrew

“…We present Reinforcement Learning via Auxiliary Task Distillation (AuxDistill), a new method that enables reinforcement learning (RL) to perform long-horizon…”
Get full text

Grounding Multimodal Large Language Models in Actions by Szot, Andrew, Mazoure, Bogdan, Agrawal, Harsh, Hjelm, Devon, Kira, Zsolt, Toshev, Alexander

“…Multimodal Large Language Models (MLLMs) have demonstrated a wide range of capabilities across many domains, including Embodied AI. In this work, we study how…”
Get full text

Generalization to New Actions in Reinforcement Learning by Jain, Ayush, Szot, Andrew, Lim, Joseph J

“…A fundamental trait of intelligence is the ability to achieve goals in the face of novel circumstances, such as making decisions from new action choices…”
Get full text

Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second by Berges, Vincent-Pierre, Szot, Andrew, Chaplot, Devendra Singh, Gokaslan, Aaron, Mottaghi, Roozbeh, Batra, Dhruv, Undersander, Eric

“…We present Galactic, a large-scale simulation and reinforcement-learning (RL) framework for robotic mobile manipulation in indoor environments. Specifically, a…”
Get full text

Adaptive Coordination in Social Embodied Rearrangement by Szot, Andrew, Jain, Unnat, Batra, Dhruv, Kira, Zsolt, Desai, Ruta, Rai, Akshara

“…We present the task of "Social Rearrangement", consisting of cooperative everyday tasks like setting up the dinner table, tidying a house or unpacking…”
Get full text

Large Language Models as Generalizable Policies for Embodied Tasks by Szot, Andrew, Schwarzer, Max, Agrawal, Harsh, Mazoure, Bogdan, Talbott, Walter, Metcalf, Katherine, Mackraz, Natalie, Hjelm, Devon, Toshev, Alexander

“…We show that large language models (LLMs) can be adapted to be generalizable policies for embodied visual tasks. Our approach, called Large LAnguage model…”
Get full text

Housekeep: Tidying Virtual Households using Commonsense Reasoning by Kant, Yash, Ramachandran, Arun, Yenamandra, Sriram, Gilitschenski, Igor, Batra, Dhruv, Szot, Andrew, Agrawal, Harsh

“…We introduce Housekeep, a benchmark to evaluate commonsense reasoning in the home for embodied AI. In Housekeep, an embodied agent must tidy a house by…”
Get full text

Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots by Puig, Xavier, Undersander, Eric, Szot, Andrew, Cote, Mikael Dallaire, Yang, Tsung-Yen, Partsey, Ruslan, Desai, Ruta, Clegg, Alexander William, Hlavac, Michal, Min, So Yeon, Vondruš, Vladimír, Gervet, Theophile, Berges, Vincent-Pierre, Turner, John M, Maksymets, Oleksandr, Kira, Zsolt, Kalakrishnan, Mrinal, Malik, Jitendra, Chaplot, Devendra Singh, Jain, Unnat, Batra, Dhruv, Rai, Akshara, Mottaghi, Roozbeh

“…We present Habitat 3.0: a simulation platform for studying collaborative human-robot tasks in home environments. Habitat 3.0 offers contributions across three…”
Get full text

Towards Open-World Mobile Manipulation in Homes: Lessons from the Neurips 2023 HomeRobot Open Vocabulary Mobile Manipulation Challenge by Yenamandra, Sriram, Ramachandran, Arun, Khanna, Mukul, Yadav, Karmesh, Vakil, Jay, Melnik, Andrew, Büttner, Michael, Harz, Leon, Brown, Lyon, Nandi, Gora Chand, PS, Arjun, Yadav, Gaurav Kumar, Kala, Rahul, Haschke, Robert, Luo, Yang, Zhu, Jinxin, Han, Yansen, Lu, Bingyi, Gu, Xuan, Liu, Qinyuan, Zhao, Yaping, Ye, Qiting, Dou, Chenxiao, Chua, Yansong, Kuzma, Volodymyr, Humennyy, Vladyslav, Partsey, Ruslan, Francis, Jonathan, Chaplot, Devendra Singh, Chhablani, Gunjan, Clegg, Alexander, Gervet, Theophile, Jain, Vidhi, Ramrakhya, Ram, Szot, Andrew, Wang, Austin, Yang, Tsung-Yen, Edsinger, Aaron, Kemp, Charlie, Shah, Binit, Kira, Zsolt, Batra, Dhruv, Mottaghi, Roozbeh, Bisk, Yonatan, Paxton, Chris

“…In order to develop robots that can effectively serve as versatile and capable home assistants, it is crucial for them to reliably perceive and interact with a…”
Get full text

Retrospectives on the Embodied AI Workshop by Deitke, Matt, Batra, Dhruv, Bisk, Yonatan, Campari, Tommaso, Chang, Angel X, Chaplot, Devendra Singh, Chen, Changan, D'Arpino, Claudia Pérez, Ehsani, Kiana, Farhadi, Ali, Fei-Fei, Li, Francis, Anthony, Gan, Chuang, Grauman, Kristen, Hall, David, Han, Winson, Jain, Unnat, Kembhavi, Aniruddha, Krantz, Jacob, Lee, Stefan, Li, Chengshu, Majumder, Sagnik, Maksymets, Oleksandr, Martín-Martín, Roberto, Mottaghi, Roozbeh, Raychaudhuri, Sonia, Roberts, Mike, Savarese, Silvio, Savva, Manolis, Shridhar, Mohit, Sünderhauf, Niko, Szot, Andrew, Talbot, Ben, Tenenbaum, Joshua B, Thomason, Jesse, Toshev, Alexander, Truong, Joanne, Weihs, Luca, Wu, Jiajun

“…We present a retrospective on the state of Embodied AI research. Our analysis focuses on 13 challenges presented at the Embodied AI Workshop at CVPR. These…”
Get full text

Habitat 2.0: Training Home Assistants to Rearrange their Habitat by Szot, Andrew, Clegg, Alex, Undersander, Eric, Wijmans, Erik, Zhao, Yili, Turner, John, Maestre, Noah, Mukadam, Mustafa, Chaplot, Devendra, Maksymets, Oleksandr, Gokaslan, Aaron, Vondrus, Vladimir, Dharur, Sameer, Meier, Franziska, Galuba, Wojciech, Chang, Angel, Kira, Zsolt, Koltun, Vladlen, Malik, Jitendra, Savva, Manolis, Batra, Dhruv

“…We introduce Habitat 2.0 (H2.0), a simulation platform for training virtual robots in interactive 3D environments and complex physics-enabled scenarios. We…”
Get full text