English
Related papers

Related papers: Cyclical Entropy Eruption: Entropy Dynamics in Age…

200 papers

Large transformer models powered by diverse data and model scale have dominated natural language modeling and computer vision and pushed the frontier of multiple AI areas. In reinforcement learning (RL), despite many efforts into…

Machine Learning · Computer Science 2023-05-29 Hao Liu , Pieter Abbeel

How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the…

Artificial Intelligence · Computer Science 2026-05-22 Mingkai Deng , Jinyu Hou , Lara Sá Neves , Varad Pimpalkhute , Taylor W. Killian , Zhengzhong Liu , Eric P. Xing

Large Language Models (LLMs) can sometimes degrade into repetitive loops, persistently generating identical word sequences. Because repetition is rare in natural human language, its frequent occurrence across diverse tasks and contexts in…

Computation and Language · Computer Science 2025-11-05 Matéo Mahaut , Francesca Franzon

In Model-Based Reinforcement Learning (MBRL), incorporating causal structures into dynamics models provides agents with a structured understanding of the environments, enabling efficient decision. Empowerment as an intrinsic motivation…

Artificial Intelligence · Computer Science 2025-02-17 Hongye Cao , Fan Feng , Meng Fang , Shaokang Dong , Tianpei Yang , Jing Huo , Yang Gao

Exposure bias describes the phenomenon that a language model trained under the teacher forcing schema may perform poorly at the inference stage when its predictions are conditioned on its previous predictions unseen from the training…

Computation and Language · Computer Science 2020-04-02 Yifan Xu , Kening Zhang , Haoyu Dong , Yuezhou Sun , Wenlong Zhao , Zhuowen Tu

Reinforcement learning (RL) has proven effective for fine-tuning large language models (LLMs), significantly enhancing their reasoning abilities in domains such as mathematics and code generation. A crucial factor influencing RL fine-tuning…

Artificial Intelligence · Computer Science 2025-10-31 Xiaoyin Chen , Jiarui Lu , Minsu Kim , Dinghuai Zhang , Jian Tang , Alexandre Piché , Nicolas Gontier , Yoshua Bengio , Ehsan Kamalloo

Standard reinforcement learning (RL) for large language model (LLM) agents typically optimizes extrinsic rewards, prioritizing isolated task completion over continual adaptation. Consequently, agents often converge to suboptimal policies…

Artificial Intelligence · Computer Science 2026-03-31 Xiaoying Zhang , Zichen Liu , Yipeng Zhang , Xia Hu , Wenqi Shao

Multi-agent inverse reinforcement learning (MIRL) can be used to learn reward functions from agents in social environments. To model realistic social dynamics, MIRL methods must account for suboptimal human reasoning and behavior.…

Artificial Intelligence · Computer Science 2021-09-06 Sage Bergerson

While LLMs exhibit impressive fluency and factual recall, they struggle with robust causal reasoning, often relying on spurious correlations and brittle patterns. Similarly, traditional Reinforcement Learning agents also lack causal…

Machine Learning · Computer Science 2025-09-26 Abi Aryan , Zac Liu

Adoption of machine learning (ML)-enabled cyber-physical systems (CPS) are becoming prevalent in various sectors of modern society such as transportation, industrial, and power grids. Recent studies in deep reinforcement learning (DRL) have…

Machine Learning · Computer Science 2020-07-15 Kai Liang Tan , Yasaman Esfandiari , Xian Yeow Lee , Aakanksha , Soumik Sarkar

Large Language Models (LLMs) have become a popular interface for human-AI interaction, supporting information seeking and task assistance through natural, multi-turn dialogue. To respond to users within multi-turn dialogues, the…

Computation and Language · Computer Science 2026-04-16 Fengran Mo , Yifan Gao , Sha Li , Hansi Zeng , Xin Liu , Zhaoxuan Tan , Xian Li , Jianshu Chen , Dakuo Wang , Meng Jiang

Equipping large language models with explicit skills has emerged as a promising paradigm for enabling autonomous agents to solve complex tasks. Agent skills can be inherently divided into general skills for broad cognitive transfer and…

Computation and Language · Computer Science 2026-05-28 Jiapeng Zhu , Jianxiang Yu , Yibo Zhao , Chengcheng Han , Qi Gu , Xunliang Cai , Xiang Li , Weining Qian

Multi-Agent Reinforcement Learning (MARL) methods find optimal policies for agents that operate in the presence of other learning agents. Central to achieving this is how the agents coordinate. One way to coordinate is by learning to…

Multiagent Systems · Computer Science 2020-04-10 Shubham Gupta , Rishi Hazra , Ambedkar Dukkipati

Deep Reinforcement Learning (RL) is remarkably effective in addressing sequential resource allocation problems in domains such as healthcare, public policy, and resource management. However, deep RL policies often lack transparency and…

Machine Learning · Computer Science 2025-02-18 Mauricio Tec , Guojun Xiong , Haichuan Wang , Francesca Dominici , Milind Tambe

Chain-of-thought (CoT) reasoning has become the default strategy for enhancing LLM capabilities, yet its application raises a fundamental question: when is explicit reasoning actually beneficial? Empirical evidence reveals a striking…

Machine Learning · Computer Science 2026-05-25 Wei Xia , Haoqing Wang , Zhi-Hong Deng , Yehui Tang

Reinforcement Learning (RL) is a semi-supervised learning paradigm which an agent learns by interacting with an environment. Deep learning in combination with RL provides an efficient method to learn how to interact with the environment is…

Sound · Computer Science 2022-03-30 Thejan Rajapakshe , Rajib Rana , Sara Khalifa , Björn W. Schuller , Jiajun Liu

Reinforcement learning (RL) is currently used in various real-life applications. RL-based solutions have the potential to generically address problems, including the ones that are difficult to solve with heuristics and meta-heuristics and,…

Machine Learning · Computer Science 2022-11-24 Rafael F. Reale , Joberto S. B. Martins

Training reasoning language models (LMs) with reinforcement learning (RL) for one-hot correctness inherently relies on the LM being able to explore and solve its task with some chance at initialization. Furthermore, a key use case of…

Machine Learning · Computer Science 2025-10-30 Edoardo Cetin , Tianyu Zhao , Yujin Tang

Goal-Conditioned Reinforcement Learning (GCRL) enables agents to autonomously acquire diverse behaviors, but faces major challenges in visual environments due to high-dimensional, semantically sparse observations. In the online setting,…

Machine Learning · Computer Science 2025-11-05 Nicolas Castanet , Olivier Sigaud , Sylvain Lamprier

Reinforcement learning (RL) offers a principled way to enhance the reasoning capabilities of large language models, yet its effectiveness hinges on training signals that remain informative as models evolve. In practice, RL progress often…

Artificial Intelligence · Computer Science 2026-05-05 Caijun Xu , Changyi Xiao , Zhongyuan Peng , Xinrun Wang , Yixin Cao