Pith. sign in

In tables, we denote values at or above 95% of the best performance in bold, following OGBench (Park et al., 2025)

The results are averaged over 8 seeds (4 seeds for pixel-based tasks), we report standard deviations after “±” in tables, 95% bootstrap confidence intervals as shaded areas in plots · 2023

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

fields

cs.LG 1

years

2025 1

verdicts

ACCEPT 1

representative citing papers

Flow Q-Learning

cs.LG · 2025-02-04 · accept · novelty 6.0

FQL trains a one-step policy to maximize Q-values while distilling a flow-matching behavioral cloning policy, outperforming many offline RL baselines.

citing papers explorer

Showing 1 of 1 citing paper.

  • Flow Q-Learning cs.LG · 2025-02-04 · accept · none · ref 12

    FQL trains a one-step policy to maximize Q-values while distilling a flow-matching behavioral cloning policy, outperforming many offline RL baselines.