按年被提到
20222022 · 1 次2026
强化学习与智能体›深度强化学习与世界模型·arXiv:2206.11795 · cs.LG

Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

Bowen Baker, Ilge Akkaya, Peter Zhokhov, Joost Huizinga, Jie Tang, Adrien Ecoffet, Brandon Houghton, Raul Sampedro, Jeff Clune · 2022
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2022-06-26 · 最近 2026-02-26
2不同的人
2活跃月份
2讨论串
85被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Pretraining on noisy, internet-scale datasets has been heavily studied as a technique for training models with broad, general capabilities for text, images, and other modalities. However, for many sequential decision domains such as robotics, video games, and computer use, publicly available data does not contain the labels required to train behavioral priors in the same way. We extend the internet-scale pretraining paradigm to sequential decision domains through semi-supervised imitation learning wherein agents learn to act by watching online unlabeled videos. Specifically, we show that with a small amount of labeled data we can train an inverse dynamics model accurate enough to label a huge unlabeled source of online data -- here, online videos of people playing Minecraft -- from which we can then train a general behavioral prior. Despite using the native human interface (mouse and keyboard at 20Hz), we show that this behavioral prior has nontrivial zero-shot capabilities and that it can be fine-tuned, with both imitation learning and reinforcement learning, to hard-exploration tasks that are impossible to learn from scratch via reinforcement learning. For many tasks our models exhibit human-level performance, and we are the first to report computer agents that can craft diamond tools, which can take proficient humans upwards of 20 minutes (24,000 environment actions) of gameplay to accomplish.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论nee1r · 2026-02

“thanks! got a lot of inspiration from VPT https://arxiv.org/abs/2206.11795 is a great paper, would recommend a read we all have various backgrounds, me particularly i did a lot of material science x ai research and just fundamental architecture research before”

The first general computer action model原评论 ↗
被提交为 story · 1 次