Reproduce “VPFlow: Value-Predictive Planning with Imperfect World Models for Offline Goal Reaching” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yunzhe Hu, Dong Xu
VPFlow trains an offline goal-reaching model to preserve estimates of progress toward requested goals rather than predict next states. It relabels future trajectory observations as goals and trains imagined latent rollouts to predict discounted returns from temporal distance. OGBench success averages 63.2% across 17 state datasets and 37.6% across 13 pixel datasets; pixel AntMaze favors CRL, 68.2% to VPFlow’s 61.0%.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.