English
Related papers

Related papers: MaskFocus: Focusing Policy Optimization on Critica…

200 papers

Diffusion models have been successfully applied in areas such as image, video, and audio generation. Recent works show their promise for sequential decision-making and dexterous manipulation, leveraging their ability to model complex action…

Robotics · Computer Science 2026-03-17 Maria Makarova , Qian Liu , Dzmitry Tsetserukou

When using a tool, the grasps used for picking it up, reposing, and holding it in a suitable pose for the desired task could be distinct. Therefore, a key challenge for autonomous in-hand tool manipulation is finding a sequence of grasps…

Robotics · Computer Science 2023-04-06 Ethan K. Gordon , Rana Soltani Zarrin

Model-based reinforcement learning (RL) algorithms allow us to combine model-generated data with those collected from interaction with the real system in order to alleviate the data efficiency problem in RL. However, designing such…

Machine Learning · Computer Science 2020-06-25 Yinlam Chow , Brandon Cui , MoonKyung Ryu , Mohammad Ghavamzadeh

Radiology report generation requires advanced medical image analysis, effective temporal reasoning, and accurate text generation. Although recent innovations, particularly multimodal large language models, have shown improved performance,…

Computation and Language · Computer Science 2025-11-11 Kai Zhang , Christopher Malon , Lichao Sun , Martin Renqiang Min

Generative design refers to computational design methods that can automatically conduct design exploration under constraints defined by designers. Among many approaches, topology optimization-based generative designs aim to explore diverse…

Computer Vision and Pattern Recognition · Computer Science 2022-10-04 Seowoo Jang , Soyoung Yoo , Namwoo Kang

Pruning is an effective method for compressing Large Language Models, but finding an optimal, non-uniform layer-wise sparsity allocation remains a key challenge. While heuristic methods are fast but yield suboptimal performance, more…

Machine Learning · Computer Science 2025-11-25 Xin Yuan , Siqi Li , Jiateng Wei , Chengrui Zhu , Yanming Wu , Qingpeng Li , Jiajun Lv , Xiaoke Lan , Jun Chen , Yong Liu

The Robust Markov Decision Process (RMDP) framework focuses on designing control policies that are robust against the parameter uncertainties due to the mismatches between the simulator model and real-world settings. An RMDP problem is…

Machine Learning · Computer Science 2022-05-17 Kishan Panaganti , Dileep Kalathil

Instruction-driven image editing with unified multimodal generative models has advanced rapidly, yet their underlying visual reasoning remains limited, leading to suboptimal performance on reasoning-centric edits. Reinforcement learning…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Hengjia Li , Liming Jiang , Qing Yan , Yizhi Song , Hao Kang , Zichuan Liu , Xin Lu , Boxi Wu , Deng Cai

Reinforcement Learning (RL) has shown exceptional performance across various applications, enabling autonomous agents to learn optimal policies through interaction with their environments. However, traditional RL frameworks often face…

Machine Learning · Computer Science 2025-09-03 Rui Liu , Anish Gupta , Erfaun Noorani , Pratap Tokekar

We present an off-policy actor-critic algorithm for Reinforcement Learning (RL) that combines ideas from gradient-free optimization via stochastic search with learned action-value function. The result is a simple procedure consisting of…

Recent advances in text-conditioned image generation diffusion models have begun paving the way for new opportunities in modern medical domain, in particular, generating Chest X-rays (CXRs) from diagnostic reports. Nonetheless, to further…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Woojung Han , Chanyoung Kim , Dayun Ju , Yumin Shim , Seong Jae Hwang

Reinforcement learning (RL) has become a promising paradigm for optimizing Retrieval-Augmented Generation (RAG) in complex reasoning tasks. However, traditional outcome-based RL approaches often suffer from reward sparsity and inefficient…

Artificial Intelligence · Computer Science 2026-01-30 Zhao Wang , Ziliang Zhao , Zhicheng Dou

Existing Maximum-Entropy (MaxEnt) Reinforcement Learning (RL) methods for continuous action spaces are typically formulated based on actor-critic frameworks and optimized through alternating steps of policy evaluation and policy…

Machine Learning · Computer Science 2024-10-29 Chen-Hao Chao , Chien Feng , Wei-Fang Sun , Cheng-Kuang Lee , Simon See , Chun-Yi Lee

We are interested in learning scalable agents for reinforcement learning that can learn from large-scale, diverse sequential data similar to current large vision and language models. To this end, this paper presents masked decision…

Machine Learning · Computer Science 2023-05-30 Fangchen Liu , Hao Liu , Aditya Grover , Pieter Abbeel

During initial iterations of training in most Reinforcement Learning (RL) algorithms, agents perform a significant number of random exploratory steps. In the real world, this can limit the practicality of these algorithms as it can lead to…

Machine Learning · Computer Science 2022-10-17 Ashish Kumar Jayant , Shalabh Bhatnagar

Reinforcement Learning (RL) enhances LLM reasoning, yet a paradox emerges as models scale: strong base models saturate standard benchmarks (e.g., MATH), yielding correct but homogeneous solutions. In such environments, the lack of failure…

Machine Learning · Computer Science 2026-04-21 Zhenwen Liang , Yujun Zhou , Sidi Lu , Xiangliang Zhang , Haitao Mi , Dong Yu

The Group Relative Policy Optimization (GRPO), a reinforcement learning method used to fine-tune large language models (LLMs), has proved its effectiveness in practical applications such as DeepSeek-R1. It raises a question whether GRPO can…

Machine Learning · Computer Science 2025-11-20 Yanchen Xu , Ziheng Jiao , Hongyuan Zhang , Xuelong Li

Reinforcement Learning (RL) is increasingly utilized to enhance the reasoning capabilities of Large Language Models (LLMs). However, effectively scaling these RL methods presents significant challenges, primarily due to the difficulty in…

Machine Learning · Computer Science 2025-09-30 Alexandre Piché , Ehsan Kamalloo , Rafael Pardinas , Xiaoyin Chen , Dzmitry Bahdanau

Reinforcement learning (RL) in continuous action spaces encounters persistent challenges, such as inefficient exploration and convergence to suboptimal solutions. To address these limitations, we propose CAMEL, a novel framework integrating…

Machine Learning · Computer Science 2025-02-18 Yanxiao Zhao , Yangge Qian , Jingyang Shan , Xiaolin Qin

In this paper, we present a deep reinforcement learning (RL) framework for iterative dialog policy optimization in end-to-end task-oriented dialog systems. Popular approaches in learning dialog policy with RL include letting a dialog agent…

Computation and Language · Computer Science 2017-09-20 Bing Liu , Ian Lane