paper-with-me

홈 › Papers

FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance

2026-05-29 · Sungha Kim, Gawon Lee, Jusuk Lee, Jonghae Park, H. Jin Kim, Daesol Cho arxiv

Maximum entropy reinforcement learning (MaxEnt-RL) enables robust exploration, yet practical implementations often restrict policies to simple Gaussians. While recent approaches incorporate expressive generative policies via importance-weighted supervised learning, they are prone to importance weight collapse, which limits their scalability in high-dimensional action spaces. Our key insight is to mitigate this limitation by localizing the sampling region, avoiding the weight degeneracy induced by importance sampling over the entire action space. To instantiate this insight, we introduce \textbf{FLAG} (\textbf{F}low policy with \textbf{L}atent-\textbf{A}ugmented \textbf{G}uidance). FLAG augments the state space with a flow latent variable and optimizes a provably consistent proxy MaxEnt-RL objective. We empirically demonstrate that FLAG enables expressive policy optimization with limited importance samples and scales to high-dimensional control tasks. Furthermore, FLAG achieves state-of-the-art performance across challenging benchmarks. Our project webpage: https://flag-rl.github.io/

📄 PDF Abstract BibTeX arXiv:2605.30749

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Discrete Probabilistic Inference as Control in Multi-path Environments

2024-02-15 · Tristan Deleu, Padideh Nouri, Nikolay Malkin, Doina Precup 외

We consider the problem of sampling from a discrete and structured distribution as a sequential decision problem, where the objective is to find a stochastic policy such that objects are sampled at the end of this sequen…

Rectifying Reinforcement Learning for Reward Matching

2024-06-04 · Haoran He, Emmanuel Bengio, Qingpeng Cai, Ling Pan

The Generative Flow Network (GFlowNet) is a probabilistic framework in which an agent learns a stochastic policy and flow functions to sample objects with probability proportional to an unnormalized reward function. GFlo…

Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

Generative Actor-Critic with Soft Bridge Policies

2026-05-09 · Ke He, Le He, Shunpu Tang, Yafei Wang 외 arxiv

Expressive generative policies such as diffusion and flow models are appealing for MaxEnt online reinforcement learning because of their ability to model multimodal and highly non-Gaussian action distributions. However, …

Reinforcement Learning

Maximum Entropy Reinforcement Learning with Diffusion Policy

2025-02-17 · Xiaoyi Dong, Jian Cheng, Xi Sheryl Zhang

The Soft Actor-Critic (SAC) algorithm with a Gaussian policy has become a mainstream implementation for realizing the Maximum Entropy Reinforcement Learning (MaxEnt RL) objective, which incorporates entropy maximization …

Efficient ExplorationMuJoCoreinforcement-learningReinforcement Learning

Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow

2024-05-22 · Chen-Hao Chao, Chien Feng, Wei-Fang Sun, Cheng-Kuang Lee 외

Existing Maximum-Entropy (MaxEnt) Reinforcement Learning (RL) methods for continuous action spaces are typically formulated based on actor-critic frameworks and optimized through alternating steps of policy evaluation an…

IngenuityMuJoCoOmniverse Isaac GymOpenAI Gym+3