English
Related papers

Related papers: Triviality Corrected Endogenous Reward

200 papers

Large Language Models employing Chain-of-Thought reasoning achieve strong performance but suffer from excessive token consumption that inflates inference costs. Existing efficiency methods such as explicit length penalties, difficulty…

Machine Learning · Computer Science 2026-04-03 Bangji Yang , Hongbo Ma , Jiajun Fan , Ge Liu

The alignment of Large Language Models (LLMs) is critically dependent on reward models trained on costly human preference data. While recent work explores bypassing this cost with AI feedback, these methods often lack a rigorous theoretical…

Computation and Language · Computer Science 2025-07-01 Yi-Chen Li , Tian Xu , Yang Yu , Xuqin Zhang , Xiong-Hui Chen , Zhongxiang Ling , Ningjing Chao , Lei Yuan , Zhi-Hua Zhou

Reasoning ability has become a defining capability of Large Language Models (LLMs), with Reinforcement Learning with Verifiable Rewards (RLVR) emerging as a key paradigm to enhance it. However, RLVR training often suffers from policy…

Machine Learning · Computer Science 2026-04-20 Xiaoyun Zhang , Xiaojian Yuan , Di Huang , Wang You , Chen Hu , Jingqing Ruan , Ai Jian , Kejiang Chen , Xing Hu

Developing scalable and generalizable reward engineering for reinforcement learning (RL) is crucial for creating general-purpose agents, especially in the challenging domain of robotic manipulation. While recent advances in reward…

Robotics · Computer Science 2025-06-25 Yuhui Chen , Haoran Li , Zhennan Jiang , Haowei Wen , Dongbin Zhao

Generating keyphrases that summarize the main points of a document is a fundamental task in natural language processing. Although existing generative models are capable of predicting multiple keyphrases for an input document as well as…

Computation and Language · Computer Science 2019-06-11 Hou Pong Chan , Wang Chen , Lu Wang , Irwin King

Modern causal language models, followed by rapid developments in discrete diffusion models, can now produce a wide variety of interesting and useful content. However, these families of models are predominantly trained to output tokens with…

Computation and Language · Computer Science 2025-08-19 Long Ma , Fangwei Zhong , Yizhou Wang

Reinforcement learning (RL) has become a central paradigm for post-training large language models (LLMs), particularly for complex reasoning tasks, yet it often suffers from exploration collapse: policies prematurely concentrate on a small…

Machine Learning · Computer Science 2026-01-16 Zhiyuan Hu , Yucheng Wang , Yufei He , Jiaying Wu , Yilun Zhao , See-Kiong Ng , Cynthia Breazeal , Anh Tuan Luu , Hae Won Park , Bryan Hooi

Sequence-to-sequence models have shown promising improvements on the temporal task of video captioning, but they optimize word-level cross-entropy loss during training. First, using policy gradient and mixed-loss methods for reinforcement…

Computation and Language · Computer Science 2017-08-09 Ramakanth Pasunuru , Mohit Bansal

We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. We show how to train the model using a combination of supervised and reinforcement learning. After teacher forcing for…

Computation and Language · Computer Science 2017-05-16 Xingdi Yuan , Tong Wang , Caglar Gulcehre , Alessandro Sordoni , Philip Bachman , Sandeep Subramanian , Saizheng Zhang , Adam Trischler

Credit assignment in reinforcement learning is the problem of measuring an action's influence on future rewards. In particular, this requires separating skill from luck, i.e. disentangling the effect of an action on rewards from that of…

Preference-based reward learning is widely used for shaping agent behavior to match a user's preference, yet its sparse binary feedback makes it especially vulnerable to causal confusion. The learned reward often latches onto spurious…

Artificial Intelligence · Computer Science 2026-03-06 Minjune Hwang , Yigit Korkmaz , Daniel Seita , Erdem Bıyık

We study the problem of generalizing an expert agent's behavior, provided through demonstrations, to new environments and/or additional constraints. Inverse Reinforcement Learning (IRL) offers a promising solution by seeking to recover the…

Machine Learning · Computer Science 2025-09-16 Filippo Lazzati , Alberto Maria Metelli

Value-based methods for reinforcement learning lack generally applicable ways to derive behavior from a value function. Many approaches involve approximate value iteration (e.g., $Q$-learning), and acting greedily with respect to the…

Machine Learning · Computer Science 2020-08-27 Alan Chan , Kris de Asis , Richard S. Sutton

Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually sparse and delayed. Learning from such signals is…

Machine Learning · Computer Science 2026-02-17 Taiwei Shi , Sihao Chen , Bowen Jiang , Linxin Song , Longqi Yang , Jieyu Zhao

Applying reinforcement learning to improve factual accuracy in knowledge-intensive question answering faces a reward design dilemma. Response-level rewards provide only coarse supervision and cannot distinguish correct from incorrect…

Computation and Language · Computer Science 2026-05-29 Shicheng Fan , Haochang Hao , Dehai Min , Weihao Liu , Philip S. Yu , Lu Cheng

As the operations of autonomous systems generally affect simultaneously several users, it is crucial that their designs account for fairness considerations. In contrast to standard (deep) reinforcement learning (RL), we investigate the…

Artificial Intelligence · Computer Science 2020-08-19 Umer Siddique , Paul Weng , Matthieu Zimmer

For many reinforcement learning (RL) applications, specifying a reward is difficult. This paper considers an RL setting where the agent obtains information about the reward only by querying an expert that can, for example, evaluate…

Machine Learning · Computer Science 2022-02-01 David Lindner , Matteo Turchetta , Sebastian Tschiatschek , Kamil Ciosek , Andreas Krause

A central belief in scaling reinforcement learning with verifiable rewards for instruction following (IF) tasks is that, a diverse mixture of verifiable hard and unverifiable soft constraints is essential for generalizing to unseen…

Machine Learning · Computer Science 2026-01-14 Yirong Zeng , Yufei Liu , Xiao Ding , Yutai Hou , Yuxian Wang , Haonan Song , Wu Ning , Dandan Tu , Qixun Zhang , Bibo Cai , Yuxiang He , Ting Liu

Large language models (LLMs) excel at complex tasks with advances in reasoning capabilities. However, existing reward mechanisms remain tightly coupled to final correctness and pay little attention to the underlying reasoning process:…

Machine Learning · Computer Science 2026-05-14 Jingyao Wang , Peizheng Guo , Wenwen Qiang , Jiahuan Zhou , Huijie Guo , Changwen Zheng , Hui Xiong

For most reinforcement learning approaches, the learning is performed by maximizing an accumulative reward that is expectedly and manually defined for specific tasks. However, in real world, rewards are emergent phenomena from the complex…

Artificial Intelligence · Computer Science 2017-05-23 Min Xu