Imagen de Portada

Helix: Evolutionary Reinforcement Learning for Open-Ended Scientific Problem Solving

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Su, Chang, Hao, Zhongkai, Zhang, Zhizhou, Xia, Zeyu, Wu, Youjia, Su, Hang, Zhu, Jun
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Preconditioning for Physics-Informed Neural Networks
por: Liu, Songming, et al.
Publicado: (2024)

On the Reuse Bias in Off-Policy Reinforcement Learning
por: Ying, Chengyang, et al.
Publicado: (2022)

Exploratory Diffusion Model for Unsupervised Reinforcement Learning
por: Ying, Chengyang, et al.
Publicado: (2025)

PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning
por: Ying, Chengyang, et al.
Publicado: (2024)

Task Aware Dreamer for Task Generalization in Reinforcement Learning
por: Ying, Chengyang, et al.
Publicado: (2023)

Accelerating PDE-Constrained Optimization by the Derivative of Neural Operators
por: Cheng, Ze, et al.
Publicado: (2025)

From Cheap Geometry to Expensive Physics: Elevating Neural Operators via Latent Shape Pretraining
por: Zhang, Zhizhou, et al.
Publicado: (2025)

Reference Neural Operators: Learning the Smooth Dependence of Solutions of PDEs on Geometric Deformations
por: Cheng, Ze, et al.
Publicado: (2024)

Improved Operator Learning by Orthogonal Attention
por: Xiao, Zipeng, et al.
Publicado: (2023)

DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training
por: Hao, Zhongkai, et al.
Publicado: (2024)

Operator Learning with Domain Decomposition for Geometry Generalization in PDE Solving
por: Huang, Jianing, et al.
Publicado: (2025)

Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning
por: Matthews, Michael, et al.
Publicado: (2024)

FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale
por: He, Runyuan, et al.
Publicado: (2026)

Focusing Robot Open-Ended Reinforcement Learning Through Users' Purposes
por: Cartoni, Emilio, et al.
Publicado: (2025)

Your Diffusion Model is Secretly a Certifiably Robust Classifier
por: Chen, Huanran, et al.
Publicado: (2024)

Self-Consistent Model-based Adaptation for Visual Reinforcement Learning
por: Zhou, Xinning, et al.
Publicado: (2025)

Helix 1.0: An Open-Source Framework for Reproducible and Interpretable Machine Learning on Tabular Scientific Data
por: Aguilar-Bejarano, Eduardo, et al.
Publicado: (2025)

Self-Rewarding Rubric-Based Reinforcement Learning for Open-Ended Reasoning
por: Ye, Zhiling, et al.
Publicado: (2025)

Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk
por: Ying, Chengyang, et al.
Publicado: (2022)

Reinforcement Learning for Solving the Pricing Problem in Column Generation: Applications to Vehicle Routing
por: Abouelrous, Abdo, et al.
Publicado: (2025)

Towards a General Framework for Continual Learning with Pre-training
por: Wang, Liyuan, et al.
Publicado: (2023)

The Autonomy-Alignment Problem in Open-Ended Learning Robots: Formalising the Purpose Framework
por: Baldassarre, Gianluca, et al.
Publicado: (2024)

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
por: Lu, Chris, et al.
Publicado: (2024)

HiDe-PET: Continual Learning via Hierarchical Decomposition of Parameter-Efficient Tuning
por: Wang, Liyuan, et al.
Publicado: (2024)

Multi-Agent Craftax: Benchmarking Open-Ended Multi-Agent Reinforcement Learning at the Hyperscale
por: Omari, Bassel Al, et al.
Publicado: (2025)

Autotelic Reinforcement Learning: Exploring Intrinsic Motivations for Skill Acquisition in Open-Ended Environments
por: Srivastava, Prakhar, et al.
Publicado: (2025)

AnyPos: Automated Task-Agnostic Actions for Bimanual Manipulation
por: Tan, Hengkai, et al.
Publicado: (2025)

GRLO: Towards Generalizable Reinforcement Learning in Open-Ended Environments from Zero
por: Yin, Shangjian, et al.
Publicado: (2026)

DéjàQ: Open-Ended Evolution of Diverse, Learnable and Verifiable Problems
por: Röpke, Willem, et al.
Publicado: (2026)

Why the Maximum Second Derivative of Activations Matters for Adversarial Robustness
por: Yu, Yunrui, et al.
Publicado: (2026)

Robust Agents in Open-Ended Worlds
por: Samvelyan, Mikayel
Publicado: (2025)

Knowledge Augmented Complex Problem Solving with Large Language Models: A Survey
por: Zheng, Da, et al.
Publicado: (2025)

A Comprehensive Survey of Continual Learning: Theory, Method and Application
por: Wang, Liyuan, et al.
Publicado: (2023)

Staggered Environment Resets Improve Massively Parallel On-Policy Reinforcement Learning
por: Bharthulwar, Sid, et al.
Publicado: (2025)

Efficient Algorithms for Mitigating Uncertainty and Risk in Reinforcement Learning
por: Su, Xihong
Publicado: (2025)

Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control
por: Chen, Huayu, et al.
Publicado: (2024)

A Motivational Architecture for Open-Ended Learning Challenges in Robots
por: Romero, Alejandro, et al.
Publicado: (2025)

AutoLibra: Agent Metric Induction from Open-Ended Human Feedback
por: Zhu, Hao, et al.
Publicado: (2025)

Neural Predictor-Corrector: Solving Homotopy Problems with Reinforcement Learning
por: Mai, Jiayao, et al.
Publicado: (2026)

Dreaming in Code for Curriculum Learning in Open-Ended Worlds
por: Mitsides, Konstantinos, et al.
Publicado: (2026)