REVIEW 6 cited by
Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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.
Forward citations
Cited by 6 Pith papers
-
In-Context World Modeling for Robotic Control
Prepending a few self-generated random interaction clips as context lets VLA policies identify novel camera viewpoints and morphologies at test time and outperform multi-view baselines without parameter updates.
-
Causally Debiased Latent Action Model for Embodied Action Conditioned World Models
Three lightweight LAM fine-tuning objectives (foreground-weighted reconstruction, primitive contrastive learning, zero-transition calibration) debias latent actions and yield stronger, cheaper robot-action following i...
-
PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments
A new open Minecraft benchmark for 2v2 LLM-agent competition, and a system, TactiCrafter, that beats its baselines on points and win rate.
-
Generative Visual Foresight Meets Task-Agnostic Pose Estimation in Robotic Table-Top Manipulation
GVF-TAPE predicts future RGB-D frames from an image and text, then extracts end-effector poses to control a robot, achieving strong success rates without action-labeled data.
-
Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents
RL post-training on 100,000 synthesized cross-view Minecraft tasks raises interaction success from 7% to 28% and transfers zero-shot to DMLab, Unreal, and a real robot.
-
Reinforcement Learning: From Algorithms To Foundation Models
A dissertation uniting the author's published results: non-exploitable Nash-DQN policies and the FightLadder benchmark for games, plus diffusion/consistency-model world models for RL — a compilation rather than new results.
Discussion (0). Continue with ORCID to comment.