36 citations · 90 across the 13 of their papers we have counts for
13 papers
Entropy-Preserving Reinforcement Learning
Aleksei Petrenko, Ben Lipkin, Kevin Chen +4
Policy gradient algorithms have driven many recent advancements in language model reasoning. An appealing property is their ability to learn from exploration on their own trajector…
Robust Autonomy Emerges from Self-Play
Marco Cusumano-Towner, David Hafner, Alex Hertzberg +9
Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust an…
Cut Your Losses in Large-Vocabulary Language Models
Erik Wijmans, Brody Huval, Alexander Hertzberg +2
As language models grow ever larger, so do their vocabularies. This has shifted the memory footprint of LLMs during training disproportionately to one single layer: the cross-entro…
Does Spatial Cognition Emerge in Frontier Models?
Santhosh Kumar Ramakrishnan, Erik Wijmans, Philipp Kraehenbuehl +1
Not yet. We present SPACE, a benchmark that systematically evaluates spatial cognition in frontier models. Our benchmark builds on decades of research in cognitive science. It eval…
Emergence of Maps in the Memories of Blind Navigation Agents
Erik Wijmans, Manolis Savva, Irfan Essa +3
Animal navigation research posits that organisms build and maintain internal spatial representations, or maps, of their environment. We ask if machines -- specifically, artificial…
PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav
Ram Ramrakhya, Dhruv Batra, Erik Wijmans +1
We study ObjectGoal Navigation -- where a virtual robot situated in a new environment is asked to navigate to an object. Prior work has shown that imitation learning (IL) using beh…
VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement
Erik Wijmans, Irfan Essa, Dhruv Batra
We present Variable Experience Rollout (VER), a technique for efficiently scaling batched on-policy reinforcement learning in heterogenous environments (where different environment…
Is Mapping Necessary for Realistic PointGoal Navigation?
Ruslan Partsey, Erik Wijmans, Naoki Yokoyama +3
Can an autonomous agent navigate in a new environment without building an explicit map? For the task of PointGoal navigation ('Go to , ') under idealized settings (no RGB-D…
Realistic PointGoal Navigation via Auxiliary Losses and Information Bottleneck
Guillermo Grande, Dhruv Batra, Erik Wijmans
We propose a novel architecture and training paradigm for training realistic PointGoal Navigation -- navigating to a target coordinate in an unseen environment under actuation and…
Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI
Santhosh K. Ramakrishnan, Aaron Gokaslan, Erik Wijmans +10
We present the Habitat-Matterport 3D (HM3D) dataset. HM3D is a large-scale dataset of 1,000 building-scale 3D reconstructions from a diverse set of real-world locations. Each scene…
Megaverse: Simulating Embodied Agents at One Million Experiences per Second
Aleksei Petrenko, Erik Wijmans, Brennan Shacklett +1
We present Megaverse, a new 3D simulation platform for reinforcement learning and embodied AI research. The efficient design of our engine enables physics-based simulation with hig…
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…
Auxiliary Tasks and Exploration Enable ObjectNav
Joel Ye, Dhruv Batra, Abhishek Das +1
ObjectGoal Navigation (ObjectNav) is an embodied task wherein agents are to navigate to an object instance in an unseen environment. Prior works have shown that end-to-end ObjectNa…