English
Related papers

Related papers: Internalizing World Models via Self-Play Finetunin…

200 papers

Large language models are increasingly deployed as autonomous agents that must plan, act, and recover from mistakes through long-horizon interaction with environments that provide rich feedback. However, prevailing outcome-driven…

Artificial Intelligence · Computer Science 2026-03-18 Rui Ge , Yichao Fu , Yuyang Qian , Junda Su , Yiming Zhao , Peng Zhao , Hao Zhang

Large language model (LLM) agents trained using reinforcement learning has achieved superhuman performance in low-cost environments like games, mathematics, and coding. However, these successes have not translated to complex domains where…

Artificial Intelligence · Computer Science 2026-02-03 Sherry Yang

Aligning Large Language Models (LLMs) to cater to different human preferences, learning new skills, and unlearning harmful behavior is an important problem. Search-based methods, such as Best-of-N or Monte-Carlo Tree Search, are performant,…

Machine Learning · Computer Science 2024-05-13 Seungwook Han , Idan Shenfeld , Akash Srivastava , Yoon Kim , Pulkit Agrawal

To interact effectively with humans in the real world, it is important for agents to understand language that describes the dynamics of the environment--that is, how the environment behaves--rather than just task instructions specifying…

Computation and Language · Computer Science 2025-12-01 Anh Nguyen , Stefan Lee

Reducing the likelihood of generating harmful and toxic output is an essential task when aligning large language models (LLMs). Existing methods mainly rely on training an external reward model (i.e., another language model) or fine-tuning…

We show that large language models (LLMs) can be adapted to be generalizable policies for embodied visual tasks. Our approach, called Large LAnguage model Reinforcement Learning Policy (LLaRP), adapts a pre-trained frozen LLM to take as…

Reinforcement learning (RL) can enable task-oriented dialogue systems to steer the conversation towards successful task completion. In an end-to-end setting, a response can be constructed in a word-level sequential decision making process…

Computation and Language · Computer Science 2020-11-19 Nurul Lubis , Christian Geishauser , Michael Heck , Hsien-chin Lin , Marco Moresi , Carel van Niekerk , Milica Gašić

Much of model-based reinforcement learning involves learning a model of an agent's world, and training an agent to leverage this model to perform a task more efficiently. While these models are demonstrably useful for agents, every…

Neural and Evolutionary Computing · Computer Science 2019-11-01 C. Daniel Freeman , Luke Metz , David Ha

Model-based reinforcement learning usually suffers from a high sample complexity in training the world model, especially for the environments with complex dynamics. To make the training for general physical environments more efficient, we…

Machine Learning · Computer Science 2022-11-03 Yao Feng , Yuhong Jiang , Hang Su , Dong Yan , Jun Zhu

Sequential planning in large state space and action space quickly becomes intractable due to combinatorial explosion of the search space. Heuristic methods, like monte-carlo tree search, though effective for large state space, but struggle…

Artificial Intelligence · Computer Science 2023-12-13 Swarna Kamal Paul

While safe reinforcement learning (RL) holds great promise for many practical applications like robotics or autonomous cars, current approaches require specifying constraints in mathematical form. Such specifications demand domain…

Computation and Language · Computer Science 2021-08-05 Tsung-Yen Yang , Michael Hu , Yinlam Chow , Peter J. Ramadge , Karthik Narasimhan

Low sample efficiency is an enduring challenge of reinforcement learning (RL). With the advent of versatile large language models (LLMs), recent works impart common-sense knowledge to accelerate policy learning for RL processes. However, we…

Computation and Language · Computer Science 2024-07-08 Fuxiang Zhang , Junyou Li , Yi-Chen Li , Zongzhang Zhang , Yang Yu , Deheng Ye

Model ensemble is a useful approach in reinforcement learning (RL) for training effective agents. Despite wide success of RL, training effective agents remains difficult due to the multitude of factors requiring careful tuning, such as…

Machine Learning · Computer Science 2025-05-22 Yiwen Song , Qianyue Hao , Qingmin Liao , Jian Yuan , Yong Li

Inference time latency has remained an open challenge for real world applications of large language models (LLMs). State-of-the-art (SOTA) speculative sampling (SpS) methods for LLMs, like EAGLE-3, use tree-based drafting to explore…

Machine Learning · Computer Science 2026-01-21 Chenan Wang , Daniel H. Shi , Haipeng Chen

Learning effective policies for real-world problems is still an open challenge for the field of reinforcement learning (RL). The main limitation being the amount of data needed and the pace at which that data can be obtained. In this paper,…

Machine Learning · Computer Science 2022-02-04 Miguel Suau , Jinke He , Matthijs T. J. Spaan , Frans A. Oliehoek

Agent skills, structured packages of procedural knowledge and executable resources that agents dynamically load at inference time, have become a reliable mechanism for augmenting LLM agents. Yet inference-time skill augmentation is…

Machine Learning · Computer Science 2026-05-18 Zhengxi Lu , Zhiyuan Yao , Jinyang Wu , Chengcheng Han , Qi Gu , Xunliang Cai , Weiming Lu , Jun Xiao , Yueting Zhuang , Yongliang Shen

The robustness of any machine learning solution is fundamentally bound by the data it was trained on. One way to generalize beyond the original training is through human-informed augmentation of the original dataset; however, it is…

Machine Learning · Computer Science 2022-09-08 Nicholas A. Ketz , Praveen K. Pilly

Offline reinforcement learning (RL) has emerged as a prevalent and effective methodology for real-world recommender systems, enabling learning policies from historical data and capturing user preferences. In offline RL, reward shaping…

Information Retrieval · Computer Science 2025-07-01 Wenzheng Shu , Yanxiang Zeng , Yongxiang Tang , Teng Sha , Ning Luo , Yanhua Cheng , Xialong Liu , Fan Zhou , Peng Jiang

A self-learning adaptive system (SLAS) uses machine learning to enable and enhance its adaptability. Such systems are expected to perform well in dynamic situations. For learning high-performance adaptation policy, some assumptions must be…

Software Engineering · Computer Science 2021-05-12 Mingyue Zhang , Jialong Li , Haiyan Zhao , Kenji Tei , Shinichi Honiden , Zhi Jin

Path planning in dynamic environments is a fundamental challenge in intelligent transportation and robotics, where obstacles and conditions change over time, introducing uncertainty and requiring continuous adaptation. While existing…

Robotics · Computer Science 2025-11-20 Jonas De Maeyer , Hossein Yarahmadi , Moharram Challenger