Imagen de Portada

expo: Exploration-prioritized policy optimization via adaptive kl regulation and gaussian curriculum sampling

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lin, Mingxiong, Gong, Zhangquan, Tang, Maowen, Li, Qian, Wang, Chuangchuang, Ma, Jian, Huang, Sutian, Tang, Kai, Lu, Haonan
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

fg-expo: Frontier-guided exploration-prioritized policy optimization via adaptive kl and gaussian curriculum
por: Lin, Mingxiong, et al.
Publicado: (2026)

Learning from Prompt itself: the Hierarchical Attribution Prompt Optimization
por: Chen, Dongyu, et al.
Publicado: (2026)

Mid-ir imaging of the bn/kl region
por: M. Robberto
Publicado: (2002)

To bootstrap or to rollout? An optimal and adaptive interpolation
por: Mou, Wenlong, et al.
Publicado: (2024)

Digital transformation in university technology expo
por: Alejandro K. Arrabal
Publicado: (2022)

Mexico's Pavilion at expo hanover 2000 / Raúl Cid
por: Cid, Raúl
Publicado: (2000)

2024 AOCS annual meeting and expo special issue
por: Silvana Martini
Publicado: (2025)

a¿Cómo vender en expos comerciales? / Arturo Gamboa
por: Gamboa, Arturo

Long-Term Client Selection for Federated Learning with Non-IID Data: A Truthful Auction Approach
por: Tan, Jinghong, et al.
Publicado: (2025)

Firefly optimization technique based test scenario generation and prioritization
por: Vikas Panthi
Publicado: (2018)

Classification of Transposed Poisson 3-Lie algebras of dimension 3
por: Yaxi, Jiang, et al.
Publicado: (2024)

Universal enveloping algebras of weighted differential Poisson algebras
por: Chen, Ying, et al.
Publicado: (2024)

Manin triples, bialgebras and Yang-Baxter equation of $A_3$-associative algebras
por: Jiang, Yaxi, et al.
Publicado: (2025)

Matched pairs and double construction bialgebras of (transposed) Poisson 3-Lie algebras
por: Zhou, Kecheng, et al.
Publicado: (2025)

Defect‐Driven Atomic Engineering: Oxygen Vacancy‐Stabilized Co Single Atoms on Ordered Ultrathin TiO 2 Nanowires for Efficient CO 2 ‐to‐Syngas Photoreduction
por: Jiawei Yan, et al.
Publicado: (2025)

No evidence of a rural‐urban divide in prioritizing agricultural policy goals
por: Nadja El Benni, et al.
Publicado: (2024)

An accelerated gradient method with adaptive restart for convex multiobjective optimization problems
por: Luo, Hao, et al.
Publicado: (2025)

The soft channels of policy diffusion: Insights from local climate change adaptation policy
por: Kai Schulze
Publicado: (2024)

Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation
por: Yu, Zhiqi, et al.
Publicado: (2026)

Synthesis of ZnO/Carbon Nanotube Composites for Enhanced Photocatalytic Performance and Its Mechanism Study
por: Jingwei Jia, et al.
Publicado: (2026)

Development and characterization of polymer composites with cotton straw fiber derived from agricultural wastes
por: Yucheng Liu, et al.
Publicado: (2024)

DV-Matcher: Deformation-based Non-Rigid Point Cloud Matching Guided by Pre-trained Visual Features
por: Chen, Zhangquan, et al.
Publicado: (2024)

Multipartite entanglement features of primordial non-gaussianities
por: Belfiglio, Alessio, et al.
Publicado: (2025)

Generating gaussian pseudorandom noise with binary sequences
por: Soto, Francisco-Javier, et al.
Publicado: (2024)

Phase-space gaussian ensemble quantum camouflage
por: Bernardini, Alex E., et al.
Publicado: (2024)

Magic phase transitions in monitored gaussian fermions
por: Tirrito, Emanuele, et al.
Publicado: (2025)

Hierarchical Meta-Reinforcement Learning via Automated Macro-Action Discovery
por: Cho, Minjae, et al.
Publicado: (2024)

Multi-Task Learning for Few-Shot Online Adaptation under Signal Temporal Logic Specifications
por: Arias, Andres, et al.
Publicado: (2024)

Sparsity-based Safety Conservatism for Constrained Offline Reinforcement Learning
por: Cho, Minjae, et al.
Publicado: (2024)

Brain imaging traits and epilepsy: Unraveling causal links via mendelian randomization
por: Fangyan Li, et al.
Publicado: (2024)

On policy iteration‐based discounted optimal control
por: Botao Dong, et al.
Publicado: (2024)

A restricted memory quasi-Newton bundle method for nonsmooth optimization on Riemannian manifolds
por: Tang, Chunming, et al.
Publicado: (2024)

Concentration of a high dimensional sub-gaussian vector
por: Spokoiny, Vladimir
Publicado: (2023)

Riemannian curvature of gaussian distribution in dual coordinate system
por: Assandje, Prosper Rosaire Mama, et al.
Publicado: (2025)

Empirical approximation of the gaussian distribution in $\mathbb{R}^d$
por: Bartl, Daniel, et al.
Publicado: (2023)

Estimating non-gaussian bias using counts of tracers
por: Dalal, Neal, et al.
Publicado: (2025)

Revisiting the temperature evolution law of the CMB with gaussian processes
por: Avila, Felipe, et al.
Publicado: (2025)

Text adaptation for speaker verification with speaker-text factorized embeddings
por: Yang, Yexin, et al.
Publicado: (2025)

ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning
por: Liang, Kun, et al.
Publicado: (2026)

Investigation and optimization of the deconvolution method for PMT waveform reconstruction
por: Tang, Jingzhe, et al.
Publicado: (2024)