Copertina

When Can Model-Free Reinforcement Learning be Enough for Thinking?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hanna, Josiah P., Corrado, Nicholas E.
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updates
di: Corrado, Nicholas E., et al.
Pubblicazione: (2023)

Multi-Robot Collaboration through Reinforcement Learning and Abstract Simulation
di: Labiosa, Adam, et al.
Pubblicazione: (2025)

On-Policy Policy Gradient Reinforcement Learning Without On-Policy Sampling
di: Corrado, Nicholas E., et al.
Pubblicazione: (2023)

AdaptThink: Reasoning Models Can Learn When to Think
di: Zhang, Jiajie, et al.
Pubblicazione: (2025)

Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning
di: Xiang, Violet, et al.
Pubblicazione: (2025)

Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling
di: Corrado, Nicholas E., et al.
Pubblicazione: (2026)

Reinforcement Learning via Auxiliary Task Distillation
di: Harish, Abhinav Narayan, et al.
Pubblicazione: (2024)

When Is Enough Not Enough? Illusory Completion in Search Agents
di: Ko, Dayoon, et al.
Pubblicazione: (2026)

Stable Offline Value Function Learning with Bisimulation-based Representations
di: Pavse, Brahma S., et al.
Pubblicazione: (2024)

Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies
di: Corrado, Nicholas E., et al.
Pubblicazione: (2025)

Adaptive Exploration for Data-Efficient General Value Function Evaluations
di: Jain, Arushi, et al.
Pubblicazione: (2024)

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning
di: Domico, Kyle, et al.
Pubblicazione: (2025)

When Few Steps Are Enough: Training-Free Acceleration of Identity-Preserved Generation
di: Zheng, Dongqi
Pubblicazione: (2026)

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning
di: Zhu, Rongzhi, et al.
Pubblicazione: (2025)

Thinkless: LLM Learns When to Think
di: Fang, Gongfan, et al.
Pubblicazione: (2025)

Base Models Know How to Reason, Thinking Models Learn When
di: Venhoff, Constantin, et al.
Pubblicazione: (2025)

Cognitive Decision Routing in Large Language Models: When to Think Fast, When to Think Slow
di: Du, Y., et al.
Pubblicazione: (2025)

Memory Retention Is Not Enough to Master Memory Tasks in Reinforcement Learning
di: Shchendrigin, Oleg, et al.
Pubblicazione: (2026)

How Much Thinking is Enough? Quantifying and Understanding Redundancy in LLM Reasoning
di: Zhai, Zhiyuan, et al.
Pubblicazione: (2026)

An Empirical Study on the Power of Future Prediction in Partially Observable Environments
di: Kwon, Jeongyeol, et al.
Pubblicazione: (2024)

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models
di: Liao, Yi, et al.
Pubblicazione: (2025)

How Clinicians Think and What AI Can Learn From It
di: Sengupta, Dipayan, et al.
Pubblicazione: (2026)

Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learning
di: Corrado, Nicholas E., et al.
Pubblicazione: (2023)

Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning
di: Gan, Siyuan, et al.
Pubblicazione: (2026)

Does Your Reasoning Model Implicitly Know When to Stop Thinking?
di: Huang, Zixuan, et al.
Pubblicazione: (2026)

Reasoning Models Can Be Effective Without Thinking
di: Ma, Wenjie, et al.
Pubblicazione: (2025)

Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation
di: Zhou, Hongyi, et al.
Pubblicazione: (2025)

When Alignment Isn't Enough: Response-Path Attacks on LLM Agents
di: Luo, Mingyu, et al.
Pubblicazione: (2026)

Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning
di: Sharma, Aman, et al.
Pubblicazione: (2025)

When to Think Fast and Slow? AMOR: Adaptive Entropy Gate for Hybrid Models
di: Zheng, Haoran, et al.
Pubblicazione: (2026)

A Unified Deep Reinforcement Learning Approach for Close Enough Traveling Salesman Problem
di: Fan, Mingfeng, et al.
Pubblicazione: (2025)

Language Models for Text Classification: Is In-Context Learning Enough?
di: Edwards, Aleksandra, et al.
Pubblicazione: (2024)

Training Emergent Joint Associations: A Reinforcement Learning Approach to Creative Thinking in Language Models
di: Singh, Mukul, et al.
Pubblicazione: (2025)

When Less is Enough: Efficient Inference via Collaborative Reasoning
di: Chen, Yilei, et al.
Pubblicazione: (2026)

Learning When to Think While Listening in Large Audio-Language Models
di: Song, Zhiyuan, et al.
Pubblicazione: (2026)

When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making
di: Liu, Jun, et al.
Pubblicazione: (2026)

Reward Is Enough: LLMs Are In-Context Reinforcement Learners
di: Song, Kefan, et al.
Pubblicazione: (2025)

When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning
di: Zhang, Xiaoyun, et al.
Pubblicazione: (2025)

Sparsely Multimodal Data Fusion
di: Bjorgaard, Josiah
Pubblicazione: (2024)

When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems
di: Rainone, Corrado, et al.
Pubblicazione: (2026)