24 citations · 86 across the 18 of their papers we have counts for
20 papers
LLM Value Functions for Credit Assignment in Agentic RL
Kaijie Zhu, Weixiang Yan, Omar Attia +3
Reinforcement learning (RL) for large language model (LLM) agents remains challenging in long-horizon tasks with sparse outcome rewards, where assigning credit to individual action…
RLTLDR: Self-improvement by Internalizing Self-generated Feedback
Michael Kirchhof, Eleonora Gualdoni, Andrew Szot +6
The common paradigm of reinforcement learning with verifiable rewards (RLVR) is to let agents make multiple attempts at a task, and optimize towards the successful ones. This becom…
Expanding LLM Agent Boundaries with Strategy-Guided Exploration
Andrew Szot, Michael Kirchhof, Omar Attia +1
Reinforcement learning (RL) has demonstrated notable success in post-training large language models (LLMs) as agents for tasks such as computer use, tool calling, and coding. Howev…
UltraCUA: A Foundation Model for Computer Use Agents with Hybrid Action
Yuhao Yang, Zhen Yang, Zi-Yi Dou +10
Computer-use agents face a fundamental limitation. They rely exclusively on primitive GUI actions (click, type, scroll), creating brittle execution chains prone to cascading failur…
Scaling Synthetic Task Generation for Agents via Exploration
Ram Ramrakhya, Andrew Szot, Omar Attia +6
Post-Training Multimodal Large Language Models (MLLMs) to build interactive agents holds promise across domains such as computer-use, web navigation, and robotics. A key challenge…
From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons
Andrew Szot, Bogdan Mazoure, Omar Attia +6
We examine the capability of Multimodal Large Language Models (MLLMs) to tackle diverse domains that extend beyond the traditional language and vision tasks these models are typica…
ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI
Ahmad Elawady, Gunjan Chhablani, Ram Ramrakhya +4
Intelligent embodied agents need to quickly adapt to new scenarios by integrating long histories of experience into decision-making. For instance, a robot in an unfamiliar house in…
Towards Open-World Mobile Manipulation in Homes: Lessons from the Neurips 2023 HomeRobot Open Vocabulary Mobile Manipulation Challenge
Sriram Yenamandra, Arun Ramachandran, Mukul Khanna +42
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 wide variety of obje…
Reinforcement Learning via Auxiliary Task Distillation
Abhinav Narayan Harish, Larry Heck, Josiah P. Hanna +2
We present Reinforcement Learning via Auxiliary Task Distillation (AuxDistill), a new method that enables reinforcement learning (RL) to perform long-horizon robot control problems…
Grounding Multimodal Large Language Models in Actions
Andrew Szot, Bogdan Mazoure, Harsh Agrawal +3
Multimodal Large Language Models (MLLMs) have demonstrated a wide range of capabilities across many domains, including Embodied AI. In this work, we study how to best ground a MLLM…
Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots
Xavier Puig, Eric Undersander, Andrew Szot +20
We present Habitat 3.0: a simulation platform for studying collaborative human-robot tasks in home environments. Habitat 3.0 offers contributions across three dimensions: (1) Accur…
Large Language Models as Generalizable Policies for Embodied Tasks
Andrew Szot, Max Schwarzer, Harsh Agrawal +6
We show that large language models (LLMs) can be adapted to be generalizable policies for embodied visual tasks. Our approach, called Large LAnguage model Reinforcement Learning Po…
Skill Transformer: A Monolithic Policy for Mobile Manipulation
Xiaoyu Huang, Dhruv Batra, Akshara Rai +1
We present Skill Transformer, an approach for solving long-horizon robotic tasks by combining conditional sequence modeling and skill modularity. Conditioned on egocentric and prop…
Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second
Vincent-Pierre Berges, Andrew Szot, Devendra Singh Chaplot +4
We present Galactic, a large-scale simulation and reinforcement-learning (RL) framework for robotic mobile manipulation in indoor environments. Specifically, a Fetch robot (equippe…
Adaptive Coordination in Social Embodied Rearrangement
Andrew Szot, Unnat Jain, Dhruv Batra +3
We present the task of "Social Rearrangement", consisting of cooperative everyday tasks like setting up the dinner table, tidying a house or unpacking groceries in a simulated mult…
BC-IRL: Learning Generalizable Reward Functions from Demonstrations
Andrew Szot, Amy Zhang, Dhruv Batra +2
How well do reward functions learned with inverse reinforcement learning (IRL) generalize? We illustrate that state-of-the-art IRL algorithms, which maximize a maximum-entropy obje…
Retrospectives on the Embodied AI Workshop
Matt Deitke, Dhruv Batra, Yonatan Bisk +36
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 challenges are grouped i…
Housekeep: Tidying Virtual Households using Commonsense Reasoning
Yash Kant, Arun Ramachandran, Sriram Yenamandra +4
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 rearranging misplaced object…
Habitat 2.0: Training Home Assistants to Rearrange their Habitat
Andrew Szot, Alex Clegg, Eric Undersander +18
We introduce Habitat 2.0 (H2.0), a simulation platform for training virtual robots in interactive 3D environments and complex physics-enabled scenarios. We make comprehensive contr…
Generalization to New Actions in Reinforcement Learning
Ayush Jain, Andrew Szot, Joseph J. Lim
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. However, standard reinforc…