English
Related papers

Related papers: Potential-Based Intrinsic Motivation: Preserving O…

200 papers

Personalized alignment of large language models seeks to adapt responses to individual user preferences, typically via reinforcement learning. A key challenge is obtaining accurate, user-specific reward signals in open-ended scenarios.…

Computation and Language · Computer Science 2026-02-13 Pinyi Zhang , Ting-En Lin , Yuchuan Wu , Jingyang Chen , Zongqi Wang , Hua Yang , Ze Xu , Fei Huang , Kai Zhang , Yongbin Li

Solving tasks with sparse rewards is one of the most important challenges in reinforcement learning. In the single-agent setting, this challenge is addressed by introducing intrinsic rewards that motivate agents to explore unseen regions of…

Machine Learning · Computer Science 2021-05-25 Shariq Iqbal , Fei Sha

Reward models (RMs) play a critical role in aligning AI behaviors with human preferences, yet they face two fundamental challenges: (1) Modality Imbalance, where most RMs are mainly focused on text and image modalities, offering limited…

Computation and Language · Computer Science 2025-10-28 Zhuoran Jin , Hongbang Yuan , Kejian Zhu , Jiachun Li , Pengfei Cao , Yubo Chen , Kang Liu , Jun Zhao

Process Reward Models (PRMs) have emerged as a promising approach to enhance the reasoning capabilities of large language models (LLMs) by guiding their step-by-step reasoning toward a final answer. However, existing PRMs either treat each…

Machine Learning · Computer Science 2026-03-02 Zheng Zhang , Ziwei Shan , Kaitao Song , Yexin Li , Kan Ren

Inverse reinforcement learning (IRL) aims to infer rewards from observed behavior, but rewards are not identified from the policy alone: many reward--value pairs can rationalize the same actions. Meaningful reward recovery therefore…

Machine Learning · Computer Science 2026-05-11 Lars van der Laan , Nathan Kallus , Aurelien Bibaut

We consider scenarios where a very accurate (often small) predictive model using restricted features is available when training a full-featured (often larger) model. This restricted model may be thought of as side-information'', and can…

Machine Learning · Computer Science 2025-04-10 Usama Muneeb , Mesrob I. Ohannessian

Reinforcement Learning faces an important challenge in partial observable environments that has long-term dependencies. In order to learn in an ambiguous environment, an agent has to keep previous perceptions in a memory. Earlier memory…

Machine Learning · Computer Science 2023-02-22 Alper Demir

Despite the success of Reinforcement Learning from Human Feedback (RLHF) in aligning language models with human values, reward hacking-or reward over-optimization-remains a major challenge. We identify two key obstacles to its mitigation:…

Machine Learning · Computer Science 2025-10-16 Yuchun Miao , Liang Ding , Sen Zhang , Rong Bao , Lefei Zhang , Dacheng Tao

Through reinforcement learning (RL) with outcome correctness rewards, large reasoning models (LRMs) with scaled inference computation have demonstrated substantial success on complex reasoning tasks. However, the one-sided reward, focused…

Computation and Language · Computer Science 2025-11-21 Jiashu Yao , Heyan Huang , Shuang Zeng , Chuwei Luo , WangJie You , Jie Tang , Qingsong Liu , Yuhang Guo , Yangyang Kang

Episodic rewards present a significant challenge in reinforcement learning. While intrinsic reward methods have demonstrated effectiveness in single-agent rein-forcement learning scenarios, their application to multi-agent reinforcement…

Artificial Intelligence · Computer Science 2025-11-24 Kesheng Chen , Wenjian Luo , Bang Zhang , Zeping Yin , Zipeng Ye

We propose a generic reward shaping approach for improving the rate of convergence in reinforcement learning (RL), called Self Improvement Based REwards, or SIBRE. The approach is designed for use in conjunction with any existing RL…

Machine Learning · Computer Science 2020-12-22 Somjit Nath , Richa Verma , Abhik Ray , Harshad Khadilkar

Large language models are typically aligned with human preferences by optimizing $\textit{reward models}$ (RMs) fitted to human feedback. However, human preferences are multi-faceted, and it is increasingly common to derive reward from a…

Biological systems often choose actions without an explicit reward signal, a phenomenon known as intrinsic motivation. The computational principles underlying this behavior remain poorly understood. In this study, we investigate an…

Artificial Intelligence · Computer Science 2023-01-05 Stas Tiomkin , Ilya Nemenman , Daniel Polani , Naftali Tishby

Reinforcement learning (RL) with sparse and deceptive rewards is challenging because non-zero rewards are rarely obtained. Hence, the gradient calculated by the agent can be stochastic and without valid information. Recent studies that…

Machine Learning · Computer Science 2024-02-08 Guojian Wang , Faguo Wu , Xiao Zhang , Jianxiang Liu

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

Efficient exploration remains a challenging problem in reinforcement learning, especially for tasks where extrinsic rewards from environments are sparse or even totally disregarded. Significant advances based on intrinsic motivation show…

Machine Learning · Computer Science 2024-04-03 Chenjia Bai , Peng Liu , Kaiyu Liu , Lingxiao Wang , Yingnan Zhao , Lei Han

Reinforcement Learning with Verifiable Rewards (RLVR) demonstrates significant potential in enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing RLVR methods are often constrained by issues such as…

Artificial Intelligence · Computer Science 2026-01-14 Jinpeng Wang , Chao Li , Ting Ye , Mengyuan Zhang , Wei Liu , Jian Luan

Multi-objective reinforcement learning (MORL) is a structured approach for optimizing tasks with multiple objectives. However, it often relies on pre-defined reward functions, which can be hard to design for balancing conflicting goals and…

Machine Learning · Computer Science 2025-07-21 Ni Mu , Yao Luan , Qing-Shan Jia

Large pretrained language models are critical components of modern NLP pipelines. Yet, they suffer from spurious correlations, poor out-of-domain generalization, and biases. Inspired by recent progress in causal machine learning, in…

Computation and Language · Computer Science 2022-11-16 Maxime Peyrard , Sarvjeet Singh Ghotra , Martin Josifoski , Vidhan Agarwal , Barun Patra , Dean Carignan , Emre Kiciman , Robert West

Providing a suitable reward function to reinforcement learning can be difficult in many real world applications. While inverse reinforcement learning (IRL) holds promise for automatically learning reward functions from demonstrations,…

Machine Learning · Computer Science 2019-10-29 Lantao Yu , Tianhe Yu , Chelsea Finn , Stefano Ermon