English
Related papers

Related papers: Sequence Generation with Guider Network

200 papers

Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermediate reasoning steps (Chain-of-Thought). Yet the mechanism by which sparse rewards drive policy…

Machine Learning · Computer Science 2026-02-03 Yuval Ran-Milo , Yotam Alexander , Shahar Mendel , Nadav Cohen

In classic Reinforcement Learning (RL), the agent maximizes an additive objective of the visited states, e.g., a value function. Unfortunately, objectives of this type cannot model many real-world applications such as experiment design,…

Machine Learning · Computer Science 2024-07-16 Riccardo De Santi , Manish Prajapat , Andreas Krause

Aligning language models (LMs) with preferences is an important problem in natural language generation. A key challenge is that preferences are typically provided at the sequence level while LM training and generation both occur at the…

Computation and Language · Computer Science 2025-01-09 Shentao Yang , Shujian Zhang , Congying Xia , Yihao Feng , Caiming Xiong , Mingyuan Zhou

Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where…

Machine Learning · Computer Science 2020-05-28 Yiming Ding , Carlos Florensa , Mariano Phielipp , Pieter Abbeel

While deep reinforcement learning techniques have led to agents that are successfully able to learn to perform a number of tasks that had been previously unlearnable, these techniques are still susceptible to the longstanding problem of…

Artificial Intelligence · Computer Science 2019-11-05 Nicholas Waytowich , Sean L. Barton , Vernon Lawhern , Garrett Warnell

Designing dense rewards is crucial for reinforcement learning (RL), yet in robotics it often demands extensive manual effort and lacks scalability. One promising solution is to view task progress as a dense reward signal, as it quantifies…

Artificial Intelligence · Computer Science 2026-05-21 Yuyang Liu , Chuan Wen , Yihang Hu , Dinesh Jayaraman , Yang Gao

In order to reveal the rationale behind model predictions, many works have exploited providing explanations in various forms. Recently, to further guarantee readability, more and more works turn to generate sentence-level human language…

Computation and Language · Computer Science 2023-02-22 Yan Liu , Xiaokang Chen , Qi Dai

Sequence generation models for dialogue are known to have several problems: they tend to produce short, generic sentences that are uninformative and unengaging. Retrieval models on the other hand can surface interesting responses, but are…

Computation and Language · Computer Science 2018-09-07 Jason Weston , Emily Dinan , Alexander H. Miller

This paper studies the constrained/safe reinforcement learning (RL) problem with sparse indicator signals for constraint violations. We propose a model-based approach to enable RL agents to effectively explore the environment with unknown…

Artificial Intelligence · Computer Science 2021-03-09 Zuxin Liu , Hongyi Zhou , Baiming Chen , Sicheng Zhong , Martial Hebert , Ding Zhao

Column generation (CG) is one of the most successful approaches for solving large-scale linear programming (LP) problems. Given an LP with a prohibitively large number of variables (i.e., columns), the idea of CG is to explicitly consider…

Optimization and Control · Mathematics 2024-04-09 Haofeng Yuan , Lichang Fang , Shiji Song

For task-oriented dialog systems, training a Reinforcement Learning (RL) based Dialog Management module suffers from low sample efficiency and slow convergence speed due to the sparse rewards in RL.To solve this problem, many strategies…

Computation and Language · Computer Science 2021-04-13 Zhengxu Hou , Bang Liu , Ruihui Zhao , Zijing Ou , Yafei Liu , Xi Chen , Yefeng Zheng

Reward models are critical for improving large language models (LLMs), particularly in reinforcement learning from human feedback (RLHF) or inference-time verification. Current reward modeling typically relies on scores of overall responses…

Machine Learning · Computer Science 2025-06-17 Chaoyang Zhou , Shunyu Liu , Zengmao Wang , Di Wang , Rong-Cheng Tu , Bo Du , Dacheng Tao

Inducing sparseness while training neural networks has been shown to yield models with a lower memory footprint but similar effectiveness to dense models. However, sparseness is typically induced starting from a dense model, and thus this…

Machine Learning · Computer Science 2022-03-30 Thomas Demeester , Johannes Deleu , Fréderic Godin , Chris Develder

Multi-label classification is an important yet challenging task in natural language processing. It is more complex than single-label classification in that the labels tend to be correlated. Existing methods tend to ignore the correlations…

Computation and Language · Computer Science 2018-06-18 Pengcheng Yang , Xu Sun , Wei Li , Shuming Ma , Wei Wu , Houfeng Wang

We show that supervised neural information retrieval (IR) models are prone to learning sparse attention patterns over passage tokens, which can result in key phrases including named entities receiving low attention weights, eventually…

Computation and Language · Computer Science 2022-04-26 Revanth Gangi Reddy , Md Arafat Sultan , Martin Franz , Avirup Sil , Heng Ji

We study a class of reinforcement learning problems where the reward signals for policy learning are generated by an internal reward model that is dependent on and jointly optimized with the policy. This interdependence between the policy…

Machine Learning · Computer Science 2023-08-28 Mengdi Li , Xufeng Zhao , Jae Hee Lee , Cornelius Weber , Stefan Wermter

Reinforcement learning (RL) has been widely adopted in post-training for large language models (LLMs) at scale. Recently, the incentivization of reasoning capabilities in LLMs from RL indicates that $\textit{proper learning methods could…

Computation and Language · Computer Science 2025-09-26 Zijun Liu , Peiyi Wang , Runxin Xu , Shirong Ma , Chong Ruan , Peng Li , Yang Liu , Yu Wu

Finding meaningful and accurate dense rewards is a fundamental task in the field of reinforcement learning (RL) that enables agents to explore environments more efficiently. In traditional RL settings, agents learn optimal policies through…

Artificial Intelligence · Computer Science 2025-12-05 Shuyuan Zhang

We introduce a new task named Story Ending Generation (SEG), whic-h aims at generating a coherent story ending from a sequence of story plot. Wepropose a framework consisting of a Generator and a Reward Manager for thistask. The Generator…

Computation and Language · Computer Science 2019-01-14 Yan Zhao , Lu Liu , Chunhua Liu , Ruoyao Yang , Dong Yu

Recent question generation (QG) approaches often utilize the sequence-to-sequence framework (Seq2Seq) to optimize the log-likelihood of ground-truth questions using teacher forcing. However, this training objective is inconsistent with…

Computation and Language · Computer Science 2020-11-03 Yuxi Xie , Liangming Pan , Dongzhe Wang , Min-Yen Kan , Yansong Feng