Papers
arxiv:2602.12829

FLAC: Maximum Entropy RL via Kinetic Energy Regularized Bridge Matching

Published on Feb 13
· Submitted by
taesiri
on Feb 16
Authors:
,
,
,
,

Abstract

Field Least-Energy Actor-Critic (FLAC) addresses challenges in maximum entropy reinforcement learning with iterative generative policies by using kinetic energy as a proxy for policy stochasticity regulation through a generalized Schrödinger bridge formulation.

AI-generated summary

Iterative generative policies, such as diffusion models and flow matching, offer superior expressivity for continuous control but complicate Maximum Entropy Reinforcement Learning because their action log-densities are not directly accessible. To address this, we propose Field Least-Energy Actor-Critic (FLAC), a likelihood-free framework that regulates policy stochasticity by penalizing the kinetic energy of the velocity field. Our key insight is to formulate policy optimization as a Generalized Schrödinger Bridge (GSB) problem relative to a high-entropy reference process (e.g., uniform). Under this view, the maximum-entropy principle emerges naturally as staying close to a high-entropy reference while optimizing return, without requiring explicit action densities. In this framework, kinetic energy serves as a physically grounded proxy for divergence from the reference: minimizing path-space energy bounds the deviation of the induced terminal action distribution. Building on this view, we derive an energy-regularized policy iteration scheme and a practical off-policy algorithm that automatically tunes the kinetic energy via a Lagrangian dual mechanism. Empirically, FLAC achieves superior or comparable performance on high-dimensional benchmarks relative to strong baselines, while avoiding explicit density estimation.

Community

Paper submitter

FLAC is a likelihood-free RL method using kinetic energy regularization and a generalized Schrödinger bridge to stay near a high-entropy reference while optimizing return, avoiding explicit density estimation.

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2602.12829 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2602.12829 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2602.12829 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.