36 citations · 90 across the 13 of their papers we have counts for
7 papers · 1 filter
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…
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…
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…