Normalizing-flow subgoal policies plus triangle-slack reweighting provably avoid Gaussian mode-averaging and filter lucky transitions in offline hierarchical GCRL.
Maximum entropy reinforcement learning via energy-based normalizing flow.Advances in Neural Information Processing Systems, 37:56136–56165, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
NFTR: From Provable Mode-Averaging to Geodesic Subgoal Selection in Offline Goal-Conditioned RL
Normalizing-flow subgoal policies plus triangle-slack reweighting provably avoid Gaussian mode-averaging and filter lucky transitions in offline hierarchical GCRL.