English
Related papers

Related papers: Reward Gaming in Conditional Text Generation

200 papers

Reinforcement Learning (RL) has enabled Large Language Models (LLMs) to achieve remarkable reasoning in domains like mathematics and coding, where verifiable rewards provide clear signals. However, extending this paradigm to financial…

Artificial Intelligence · Computer Science 2026-01-09 Rui Sun , Yifan Sun , Sheng Xu , Li Zhao , Jing Li , Daxin Jiang , Cheng Hua , Zuo Bai

Recent advances in reinforcement learning have inspired increasing interest in learning user modeling adaptively through dynamic interactions, e.g., in reinforcement learning based recommender systems. Reward function is crucial for most of…

Machine Learning · Computer Science 2021-05-06 Xiaocong Chen , Lina Yao , Xianzhi Wang , Aixin Sun , Wenjie Zhang , Quan Z. Sheng

We transform reinforcement learning (RL) into a form of supervised learning (SL) by turning traditional RL on its head, calling this Upside Down RL (UDRL). Standard RL predicts rewards, while UDRL instead uses rewards as task-defining…

Artificial Intelligence · Computer Science 2020-06-24 Juergen Schmidhuber

Reinforcement Learning from Human Feedback (RLHF) or Verifiable Rewards (RLVR) are two key steps in the post-training of modern Language Models (LMs). A common problem is reward hacking, where the policy may exploit inaccuracies of the…

Machine Learning · Computer Science 2026-02-23 Johannes Ackermann , Michael Noukhovitch , Takashi Ishida , Masashi Sugiyama

The inherent uncertainty in the environmental transition model of Reinforcement Learning (RL) necessitates a delicate balance between exploration and exploitation. This balance is crucial for optimizing computational resources to accurately…

Machine Learning · Computer Science 2025-05-21 Yongxin Deng , Xihe Qiu , Jue Chen , Xiaoyu Tan

Reward-guided text generation (RGTG) has emerged as a viable alternative to offline reinforcement learning from human feedback (RLHF). RGTG methods can align baseline language models to human preferences without further training like in…

Machine Learning · Computer Science 2025-07-08 Ahmad Rashid , Ruotian Wu , Rongqi Fan , Hongliang Li , Agustinus Kristiadi , Pascal Poupart

Reinforcement learning (RL) is a popular approach for robotic path planning in uncertain environments. However, the control policies trained for an RL agent crucially depend on user-defined, state-based reward functions. Poorly designed…

Artificial Intelligence · Computer Science 2024-12-05 Anand Balakrishnan , Stefan Jakšić , Edgar A. Aguilar , Dejan Ničković , Jyotirmoy V. Deshmukh

We investigate how reinforcement learning can be used to train level-designing agents. This represents a new approach to procedural content generation in games, where level design is framed as a game, and the content generator itself is…

Machine Learning · Computer Science 2020-08-14 Ahmed Khalifa , Philip Bontrager , Sam Earle , Julian Togelius

Reinforcement learning (RL) has shown its strength in challenging sequential decision-making problems. The reward function in RL is crucial to the learning performance, as it serves as a measure of the task completion degree. In real-world…

Machine Learning · Computer Science 2024-02-13 Siyuan Li , Shijie Han , Yingnan Zhao , By Liang , Peng Liu

As humans increasingly share environments with diverse agents powered by RL, LLMs, and beyond, the ability to explain agent policies in natural language is vital for reliable coexistence. We introduce a general-purpose framework that trains…

Computation and Language · Computer Science 2026-02-13 Xinyi Yang , Liang Zeng , Heng Dong , Chao Yu , Xiaoran Wu , Huazhong Yang , Yu Wang , Milind Tambe , Tonghan Wang

In recent years, with the development of deep learning, text generation technology has undergone great changes and provided many kinds of services for human beings, such as restaurant reservation and daily communication. The automatically…

Computation and Language · Computer Science 2020-12-25 Bin Guo , Hao Wang , Yasan Ding , Wei Wu , Shaoyang Hao , Yueqi Sun , Zhiwen Yu

Controlled generation refers to the problem of creating text that contains stylistic or semantic attributes of interest. Many approaches reduce this problem to training a predictor of the desired attribute. For example, researchers hoping…

Computation and Language · Computer Science 2023-06-02 Carolina Zheng , Claudia Shi , Keyon Vafa , Amir Feder , David M. Blei

Reward hacking -- where RL agents exploit gaps in misspecified reward functions -- has been widely observed, but not yet systematically studied. To understand how reward hacking arises, we construct four RL environments with misspecified…

Machine Learning · Computer Science 2022-02-15 Alexander Pan , Kush Bhatia , Jacob Steinhardt

In this paper, we introduce Reward-RAG, a novel approach designed to enhance the Retrieval-Augmented Generation (RAG) model through Reward-Driven Supervision. Unlike previous RAG methodologies, which focus on training language models (LMs)…

Computation and Language · Computer Science 2024-10-08 Thang Nguyen , Peter Chin , Yu-Wing Tai

Language models are capable of iteratively improving their outputs based on natural language feedback, thus enabling in-context optimization of user preference. In place of human users, a second language model can be used as an evaluator,…

Computation and Language · Computer Science 2024-07-08 Jane Pan , He He , Samuel R. Bowman , Shi Feng

Analyzing the handwriting generation process is an important issue and has been tackled by various generation models, such as kinematics based models and stochastic models. In this study, we use a reinforcement learning (RL) framework to…

Computer Vision and Pattern Recognition · Computer Science 2020-09-24 Keisuke Kanda , Brian Kenji Iwana , Seiichi Uchida

While reinforcement learning can effectively improve language generation models, it often suffers from generating incoherent and repetitive phrases \cite{paulus2017deep}. In this paper, we propose a novel repetition normalized adversarial…

Computation and Language · Computer Science 2019-02-20 Peng Xu , Pascale Fung

In offline reinforcement learning (RL), learning from fixed datasets presents a promising solution for domains where real-time interaction with the environment is expensive or risky. However, designing dense reward signals for offline…

Machine Learning · Computer Science 2025-04-15 Younghwan Lee , Tung M. Luu , Donghoon Lee , Chang D. Yoo

Reinforcement Learning (RL) agents require the specification of a reward signal for learning behaviours. However, introduction of corrupt or stochastic rewards can yield high variance in learning. Such corruption may be a direct result of…

Machine Learning · Computer Science 2018-11-09 Joshua Romoff , Peter Henderson , Alexandre Piché , Vincent Francois-Lavet , Joelle Pineau

Despite numerous successes, the field of reinforcement learning (RL) remains far from matching the impressive generalisation power of human behaviour learning. One possible way to help bridge this gap be to provide RL agents with richer,…

Computation and Language · Computer Science 2023-12-11 Sabrina McCallum , Max Taylor-Davies , Stefano V. Albrecht , Alessandro Suglia
‹ Prev 1 3 4 5 6 7 10 Next ›