Imagen de Portada

When Maximum Entropy Misleads Policy Optimization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Ruipeng, Chang, Ya-Chien, Gao, Sicun
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Extremum-Seeking Action Selection for Accelerating Policy Optimization
por: Chang, Ya-Chien, et al.
Publicado: (2024)

Improving Value Estimation Critically Enhances Vanilla Policy Gradient
por: Wang, Tao, et al.
Publicado: (2025)

Learning Quadruped Walking from Seconds of Demonstration
por: Zhang, Ruipeng, et al.
Publicado: (2026)

Fractal Landscapes in Policy Optimization
por: Wang, Tao, et al.
Publicado: (2023)

Activation-Descent Regularization for Input Optimization of ReLU Networks
por: Yu, Hongzhan, et al.
Publicado: (2024)

Mollification Effects of Policy Gradient Methods
por: Wang, Tao, et al.
Publicado: (2024)

Maximum Entropy Reinforcement Learning with Diffusion Policy
por: Dong, Xiaoyi, et al.
Publicado: (2025)

Maximum Entropy On-Policy Actor-Critic via Entropy Advantage Estimation
por: Choe, Jean Seong Bjorn, et al.
Publicado: (2024)

Improving Compositional Generation with Diffusion Models Using Lift Scores
por: Yu, Chenning, et al.
Publicado: (2025)

Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents
por: Sun, Chung-En, et al.
Publicado: (2024)

ESPO: Entropy Importance Sampling Policy Optimization
por: Sheng, Yuepeng, et al.
Publicado: (2025)

Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL
por: Zhan, Guojian, et al.
Publicado: (2025)

Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization
por: Xu, Huimin, et al.
Publicado: (2026)

Maximum Entropy Exploration Without the Rollouts
por: Adamczyk, Jacob, et al.
Publicado: (2026)

Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement
por: Wen, Muning, et al.
Publicado: (2024)

Deriving the Scaled-Dot-Function via Maximum Likelihood Estimation and Maximum Entropy Approach
por: Ma, Jiyong
Publicado: (2025)

ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy
por: Li, Hongming, et al.
Publicado: (2024)

When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?
por: Hatgis-Kessell, Stephane, et al.
Publicado: (2026)

FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control
por: Xue, Jun, et al.
Publicado: (2026)

Reward-Punishment Reinforcement Learning with Maximum Entropy
por: Wang, Jiexin, et al.
Publicado: (2024)

Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead
por: Kang, Feiyang, et al.
Publicado: (2025)

ERPO: Token-Level Entropy-Regulated Policy Optimization for Large Reasoning Models
por: Yu, Song, et al.
Publicado: (2026)

Diffusion-Augmented Markov Decision Processes for Maximum Entropy Reinforcement Learning
por: Sanokowski, Sebastian, et al.
Publicado: (2025)

Agentic Entropy-Balanced Policy Optimization
por: Dong, Guanting, et al.
Publicado: (2025)

Beyond Importance Sampling: Rejection-Gated Policy Optimization
por: Sun, Ziwu, et al.
Publicado: (2026)

Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based Models
por: Yoon, Sangwoong, et al.
Publicado: (2024)

FLAC: Maximum Entropy RL via Kinetic Energy Regularized Bridge Matching
por: Lv, Lei, et al.
Publicado: (2026)

Boosting Maximum Entropy Reinforcement Learning via One-Step Flow Matching
por: Li, Zeqiao, et al.
Publicado: (2026)

Maximum Redundancy Pruning: A Principle-Driven Layerwise Sparsity Allocation for LLMs
por: Gao, Chang, et al.
Publicado: (2025)

EP-GRPO: Entropy-Progress Aligned Group Relative Policy Optimization with Implicit Process Guidance
por: Yu, Song, et al.
Publicado: (2026)

Fibration Policy Optimization
por: Li, Chang, et al.
Publicado: (2026)

Policy Gradient with Adaptive Entropy Annealing for Continual Fine-Tuning
por: Zhang, Yaqian, et al.
Publicado: (2026)

Maximum Entropy Behavior Exploration for Sim2Real Zero-Shot Reinforcement Learning
por: Hu, Jiajun, et al.
Publicado: (2026)

Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios
por: Dang, Yunkai, et al.
Publicado: (2024)

Decision Flow Policy Optimization
por: Hu, Jifeng, et al.
Publicado: (2025)

Towards Flash Thinking via Decoupled Advantage Policy Optimization
por: Tan, Zezhong, et al.
Publicado: (2025)

Learning to Embed Distributions via Maximum Kernel Entropy
por: Kachaiev, Oleksii, et al.
Publicado: (2024)

PSPO*: An Effective Process-supervised Policy Optimization for Reasoning Alignment
por: Li, Jiawei, et al.
Publicado: (2024)

DiPRL: Learning Discrete Programmatic Policies via Architecture Entropy Regularization
por: Hu, Chengpeng, et al.
Publicado: (2026)

On-Policy Optimization of ANFIS Policies Using Proximal Policy Optimization
por: Shankar, Kaaustaaub, et al.
Publicado: (2025)