English
Related papers

Related papers: Prism: Policy Reuse via Interpretable Strategy Map…

200 papers

Semantic top-K selection with cross-encoder rerankers underpins on-device AI services, such as retrieval-augmented generation, agent memory, and personalized recommendation. However, its latency and memory demands dominate end-to-end…

Machine Learning · Computer Science 2026-03-25 Jiahao Zhou , Chengliang Lin , Dingji Li , Mingkai Dong , Haibo Chen

Transfer learning can greatly speed up reinforcement learning for a new task by leveraging policies of relevant tasks. Existing works of policy reuse either focus on only selecting a single best source policy for transfer without…

Artificial Intelligence · Computer Science 2019-03-11 Siyuan Li , Fangda Gu , Guangxiang Zhu , Chongjie Zhang

Existing methods usually leverage a fixed strategy, such as natural language reasoning, code-augmented reasoning, tool-integrated reasoning, or ensemble-based reasoning, to guide Large Language Models (LLMs) to perform mathematical…

Artificial Intelligence · Computer Science 2025-09-30 Shihao Qi , Jie Ma , Ziang Yin , Lingling Zhang , Jian Zhang , Jun Liu , Feng Tian , Tongliang Liu

Training interpretable concept-based policies requires practitioners to manually select which human-understandable concepts an agent should reason with when making sequential decisions. This selection demands domain expertise, is…

Machine Learning · Computer Science 2026-04-07 Naveen Raman , Stephanie Milani , Fei Fang

Reinforcement learning (RL) algorithms struggle with learning optimal policies for tasks where reward feedback is sparse and depends on a complex sequence of events in the environment. Probabilistic reward machines (PRMs) are finite-state…

Machine Learning · Computer Science 2025-10-20 Jan Corazza , Hadi Partovi Aria , Daniel Neider , Zhe Xu

With the rapid progress of large language models (LLMs), financial information retrieval has become a critical industrial application. Extracting task-relevant information from lengthy financial filings is essential for both operational and…

Artificial Intelligence · Computer Science 2026-04-07 Chun Chet Ng , Jia Yu Lim , Wei Zeng Low

This paper introduces a novel causal framework for multi-stage decision-making in natural language action spaces where outcomes are only observed after a sequence of actions. While recent approaches like Proximal Policy Optimization (PPO)…

Computation and Language · Computer Science 2025-02-26 Bohan Zhang , Yixin Wang , Paramveer S. Dhillon

Reinforcement Learning (RL) algorithms are known to scale poorly to environments with many available actions, requiring numerous samples to learn an optimal policy. The traditional approach of considering the same fixed action space in…

Machine Learning · Computer Science 2023-05-15 Leo Ardon , Alberto Pozanco , Daniel Borrajo , Sumitra Ganesh

In reinforcement learning from human feedback, preference-based reward models play a central role in aligning large language models to human-aligned behavior. However, recent studies show that these models are prone to reward hacking and…

Artificial Intelligence · Computer Science 2025-10-23 Wenqian Ye , Guangtao Zheng , Aidong Zhang

Automated interpretability research aims to identify concepts encoded in neural network features to enhance human understanding of model behavior. Within the context of large language models (LLMs) for natural language processing (NLP),…

Machine Learning · Computer Science 2025-11-13 Laura Kopf , Nils Feldhus , Kirill Bykov , Philine Lou Bommer , Anna Hedström , Marina M. -C. Höhne , Oliver Eberle

Large Language Models are rapidly emerging as web-native interfaces to social platforms. On the social web, users frequently have ambiguous and dynamic goals, making complex intent understanding-rather than single-turn execution-the…

Artificial Intelligence · Computer Science 2026-01-27 Zenghua Liao , Jinzhi Liao , Xiang Zhao

Long-range tasks demand reasoning over long inputs. However, existing solutions are limited, e.g., long-context models require large compute budgets, parameter-efficient fine-tuning (PEFT) needs training data, and retrieval-augmented…

Artificial Intelligence · Computer Science 2025-08-26 Dulhan Jayalath , James Bradley Wendt , Nicholas Monath , Sandeep Tata , Beliz Gunel

Visual coverage path planning with unmanned aerial vehicles (UAVs) requires agents to strategically coordinate UAV motion and camera control to maximize coverage, minimize redundancy, and maintain battery efficiency. Traditional…

Robotics · Computer Science 2025-07-15 Venkat Margapuri

Large model training beyond tens of thousands of GPUs is an uncharted territory. At such scales, disruptions to the training process are not a matter of if, but a matter of when -- a stochastic process degrading training productivity.…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-14 Alicia Golden , Michael Kuchnik , Samuel Hsia , Zachary DeVito , Gu-Yeon Wei , David Brooks , Carole-Jean Wu

Reinforcement learning (RL) policies often fail to generalize to new robots, tasks, or environments with different physical parameters, a challenge that limits their real-world applicability. This paper presents a simple, zero-shot transfer…

Machine Learning · Computer Science 2025-10-13 Francisco Pascoa , Ian Lalonde , Alexandre Girard

In this paper, we propose a new solution to reward adaptation (RA) in reinforcement learning, where the agent adapts to a target reward function based on one or more existing source behaviors learned a priori under the same domain dynamics…

Machine Learning · Computer Science 2025-10-23 Kevin Vora , Yu Zhang

Matrix functions such as square root, inverse roots, and orthogonalization play a central role in preconditioned gradient methods for neural network training. This has motivated the development of iterative algorithms that avoid explicit…

Machine Learning · Computer Science 2026-01-30 Shenghao Yang , Zhichao Wang , Oleg Balabanov , N. Benjamin Erichson , Michael W. Mahoney

In real-world decision making tasks, it is critical for data-driven reinforcement learning methods to be both stable and sample efficient. On-policy methods typically generate reliable policy improvement throughout training, while…

Machine Learning · Computer Science 2021-11-02 James Queeney , Ioannis Ch. Paschalidis , Christos G. Cassandras

Recent advances in reinforcement learning have shown that language models can develop sophisticated reasoning through training on tasks with verifiable rewards, but these approaches depend on human-curated problem-answer pairs and…

Artificial Intelligence · Computer Science 2026-03-03 Bo Liu , Leon Guertler , Simon Yu , Zichen Liu , Penghui Qi , Daniel Balcells , Mickel Liu , Cheston Tan , Weiyan Shi , Min Lin , Wee Sun Lee , Natasha Jaques

We present CREST, an approach for causal reasoning in simulation to learn the relevant state space for a robot manipulation policy. Our approach conducts interventions using internal models, which are simulations with approximate dynamics…

Robotics · Computer Science 2022-03-15 Tabitha Edith Lee , Jialiang Zhao , Amrita S. Sawhney , Siddharth Girdhar , Oliver Kroemer