We present PoliFormer (Policy Transformer), an RGB-only indoor navigation
agent trained end-to-end with reinforcement learning at scale that generalizes
to the real-world without adaptation despite being trained purely in
simulation. PoliFormer uses a foundational vision transformer encoder with a
causal transformer decoder enabling long-term memory and reasoning. It is
trained for hundreds of millions of interactions across diverse environments,
leveraging parallelized, multi-machine rollouts for efficient training with
high throughput. PoliFormer is a masterful navigator, producing
state-of-the-art results across two distinct embodiments, the LoCoBot and
Stretch RE-1 robots, and four navigation benchmarks. It breaks through the
plateaus of previous work, achieving an unprecedented 85.5% success rate in
object goal navigation on the CHORES-S benchmark, a 28.5% absolute improvement.
PoliFormer can also be trivially extended to a variety of downstream
applications such as object tracking, multi-object navigation, and
open-vocabulary navigation with no finetuning.

我们提出了 PoliFormer（Policy Transformer），这是一个使用强化学习进行训练的 RGB 室内导航代理，采用规模化的端到端训练，能够在真实世界中无需适应即可进行泛化，尽管它是纯在模拟环境中训练的。PoliFormer 使用基本的视觉 Transformer 编码器和因果 Transformer 解码器，实现了长期记忆和推理。它通过数亿次的交互在各种环境下进行训练，利用并行化、多机器人卷积进行高效的训练，输出了两个不同任务（LoCoBot 和 Stretch RE-1 机器人）和四个导航基准测试的尖端结果。相比之前的工作，它突破了瓶颈，实现了在 CHORES-S 基准测试的物体目标导航领域的前所未有的 85.5% 成功率，绝对改进幅度为 28.5%。PoliFormer 还可以轻松扩展到多种下游应用，如物体追踪、多物体导航和无需微调的开放词汇导航。