English
Related papers

Related papers: Dual-Granularity Contrastive Reward via Generated …

200 papers

Balancing multiple objectives is critical for user satisfaction in modern recommender and search systems, yet current Multi-Task Fusion (MTF) methods rely on static, manually-tuned weights that fail to capture individual user intent. While…

Machine Learning · Computer Science 2025-10-13 Tingfeng Hong , Pingye Ren , Xinlong Xiao , Chao Wang , Chenyi Lei , Wenwu Ou , Han Li

We study the problem of sample efficient reinforcement learning, where prior data such as demonstrations are provided for initialization in lieu of a dense reward signal. A natural approach is to incorporate an imitation learning objective,…

Machine Learning · Computer Science 2025-06-10 Perry Dong , Alec M. Lessing , Annie S. Chen , Chelsea Finn

Reward function design and exploration time are arguably the biggest obstacles to the deployment of reinforcement learning (RL) agents in the real world. In many real-world tasks, designing a reward function takes considerable hand…

Computer Vision and Pattern Recognition · Computer Science 2017-06-14 Pierre Sermanet , Kelvin Xu , Sergey Levine

We consider the problem of learning from sparse and underspecified rewards, where an agent receives a complex input, such as a natural language instruction, and needs to generate a complex response, such as an action sequence, while only…

Machine Learning · Computer Science 2020-06-23 Rishabh Agarwal , Chen Liang , Dale Schuurmans , Mohammad Norouzi

Visual paragraph generation aims to automatically describe a given image from different perspectives and organize sentences in a coherent way. In this paper, we address three critical challenges for this task in a reinforcement learning…

Computer Vision and Pattern Recognition · Computer Science 2019-08-30 Yadan Luo , Zi Huang , Zheng Zhang , Ziwei Wang , Jingjing Li , Yang Yang

To overcome the sparse reward challenge in reinforcement learning (RL) for agents based on large language models (LLMs), we propose Mutual Information Self-Evaluation (MISE), an RL paradigm that utilizes hindsight generative self-evaluation…

Computation and Language · Computer Science 2026-04-14 Jiashu Yao , Heyan Huang , Zeming Liu , Yuhang Guo

With the growing use of Retrieval-Augmented Generation (RAG), training large language models (LLMs) for context-sensitive reasoning and faithfulness is increasingly important. Existing RAG-oriented reinforcement learning (RL) methods rely…

Computation and Language · Computer Science 2026-03-06 Zhehao Tan , Yihan Jiao , Dan Yang , Junjie Wang , Duolin Sun , Jie Feng , Xidong Wang , Lei Liu , Yue Shen , Jian Wang , Jinjie Gu

Offline safe reinforcement learning often requires policies to adapt at deployment time to safety budgets that vary across episodes or change within a single episode. While diffusion-based planners enable flexible trajectory generation,…

Machine Learning · Computer Science 2026-05-06 Rufeng Chen , Zhaofan Zhang , Zhejiang Yang , Hechang Chen , Sihong Xie

Many reinforcement learning (RL) tasks have specific properties that can be leveraged to modify existing RL algorithms to adapt to those tasks and further improve performance, and a general class of such properties is the multiple reward…

Machine Learning · Computer Science 2019-11-07 Zichuan Lin , Li Zhao , Derek Yang , Tao Qin , Guangwen Yang , Tie-Yan Liu

Synthetic data is crucial for advancing autonomous driving (AD) systems, yet current state-of-the-art video generation models, despite their visual realism, suffer from subtle geometric distortions that limit their utility for downstream…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Tianyi Yan , Wencheng Han , Xia Zhou , Xueyang Zhang , Kun Zhan , Cheng-zhong Xu , Jianbing Shen

Rewards play a crucial role in reinforcement learning. To arrive at the desired policy, the design of a suitable reward function often requires significant domain expertise as well as trial-and-error. Here, we aim to minimize the effort…

Robotics · Computer Science 2020-11-18 Zheng Wu , Wenzhao Lian , Vaibhav Unhelkar , Masayoshi Tomizuka , Stefan Schaal

The objective of many real-world tasks is complex and difficult to procedurally specify. This makes it necessary to use reward or imitation learning algorithms to infer a reward or policy directly from human data. Existing benchmarks for…

Machine Learning · Computer Science 2020-12-03 Pedro Freire , Adam Gleave , Sam Toyer , Stuart Russell

Reward design remains a significant bottleneck in applying reinforcement learning (RL) to real-world problems. A popular alternative is reward learning, where reward functions are inferred from human feedback rather than manually specified.…

Machine Learning · Computer Science 2026-01-16 Chaitanya Kharyal , Calarina Muslimani , Matthew E. Taylor

Reinforcement Learning (RL) has become a key approach for enhancing the reasoning capabilities of large language models. However, prevalent RL approaches like proximal policy optimization and group relative policy optimization suffer from…

Machine Learning · Computer Science 2026-02-02 Jingtong Gao , Ling Pan , Yejing Wang , Rui Zhong , Chi Lu , Maolin Wang , Qingpeng Cai , Peng Jiang , Xiangyu Zhao

Applying reinforcement learning (RL) to sparse reward domains is notoriously challenging due to insufficient guiding signals. Common RL techniques for addressing such domains include (1) learning from demonstrations and (2) curriculum…

Machine Learning · Computer Science 2023-03-29 Vaibhav Bajaj , Guni Sharon , Peter Stone

Designing reward functions is a challenging problem in AI and robotics. Humans usually have a difficult time directly specifying all the desirable behaviors that a robot needs to optimize. One common approach is to learn reward functions…

Robotics · Computer Science 2020-06-05 Erdem Bıyık , Nicolas Huynh , Mykel J. Kochenderfer , Dorsa Sadigh

Our goal is to accurately and efficiently learn reward functions for autonomous robots. Current approaches to this problem include inverse reinforcement learning (IRL), which uses expert demonstrations, and preference-based learning, which…

Robotics · Computer Science 2019-06-24 Malayandi Palan , Nicholas C. Landolfi , Gleb Shevchuk , Dorsa Sadigh

Efficient exploration in multi-agent reinforcement learning (MARL) is a challenging problem when receiving only a team reward, especially in environments with sparse rewards. A powerful method to mitigate this issue involves crafting dense…

Machine Learning · Computer Science 2025-07-28 Xuefei Wu , Xiao Yin , Yuanyang Zhu , Chunlin Chen

Reinforcement learning (RL) has recently become the dominant paradigm for strengthening the reasoning abilities of large language models (LLMs). Yet the rule-based reward functions commonly used on mathematical or programming benchmarks…

Artificial Intelligence · Computer Science 2025-09-09 Haoyang He , Zihua Rong , Kun Ji , Chenyang Li , Qing Huang , Chong Xia , Lan Yang , Honggang Zhang

While most prior work in video generation relies on bidirectional architectures, recent efforts have sought to adapt these models into autoregressive variants to support near real-time generation. However, such adaptations often depend…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Jingran Zhang , Ning Li , Yuanhao Ban , Andrew Bai , Justin Cui