GenPO++ achieves exact Jacobian-free likelihood ratio computation for generative flow policies by embedding history states as auxiliary memory in a high-order reversible ODE solver.
Boosting Trust Region Policy Optimization by Normalizing Flows Policy
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We propose to improve trust region policy search with normalizing flows policy. We illustrate that when the trust region is constructed by KL divergence constraints, normalizing flows policy generates samples far from the 'center' of the previous policy iterate, which potentially enables better exploration and helps avoid bad local optima. Through extensive comparisons, we show that the normalizing flows policy significantly improves upon baseline architectures especially on high-dimensional tasks with complex dynamics.
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GenPO++: Generative Policy Optimization with Jacobian-free Likelihood Ratios
GenPO++ achieves exact Jacobian-free likelihood ratio computation for generative flow policies by embedding history states as auxiliary memory in a high-order reversible ODE solver.