English
Related papers

Related papers: Diminishing Return of Value Expansion Methods

200 papers

The aim of multi-task reinforcement learning is two-fold: (1) efficiently learn by training against multiple tasks and (2) quickly adapt, using limited samples, to a variety of new tasks. In this work, the tasks correspond to reward…

Machine Learning · Computer Science 2019-11-05 Nicholas C. Landolfi , Garrett Thomas , Tengyu Ma

Reinforcement learning (RL) has emerged as a powerful method for improving the reasoning abilities of large language models (LLMs). Outcome-based RL, which rewards policies solely for the correctness of the final answer, yields substantial…

Machine Learning · Computer Science 2025-09-09 Yuda Song , Julia Kempe , Remi Munos

Model-based reinforcement learning uses models to plan, where the predictions and policies of an agent can be improved by using more computation without additional data from the environment, thereby improving sample efficiency. However,…

Machine Learning · Computer Science 2023-02-22 Animesh Kumar Paul , Videh Raj Nema

Ensemble models are powerful model building tools that are developed with a focus to improve the accuracy of model predictions. They find applications in time series forecasting in varied scenarios including but not limited to process…

Learning to sample from intractable distributions over discrete sets without relying on corresponding training data is a central problem in a wide range of fields, including Combinatorial Optimization. Currently, popular deep learning-based…

Machine Learning · Computer Science 2025-08-25 Sebastian Sanokowski , Sepp Hochreiter , Sebastian Lehner

Retrieval-augmented generation (RAG) systems traditionally employ sophisticated training strategies to enhance robustness against retrieval noise. In this work, we investigate a critical question: does the benefit of these complex robust…

Computation and Language · Computer Science 2025-10-06 Hanxing Ding , Shuchang Tao , Liang Pang , Zihao Wei , Liwei Chen , Kun Xu , Huawei Shen , Xueqi Cheng

A promising way to improve the sample efficiency of reinforcement learning is model-based methods, in which many explorations and evaluations can happen in the learned models to save real-world samples. However, when the learned model has a…

Machine Learning · Computer Science 2022-09-14 Haoxin Lin , Yihao Sun , Jiaji Zhang , Yang Yu

Model-based reinforcement learning (MBRL) seeks to enhance data efficiency by learning a model of the environment and generating synthetic rollouts from it. However, accumulated model errors during these rollouts can distort the data…

Machine Learning · Computer Science 2025-04-09 Bernd Frauenknecht , Devdutt Subhasish , Friedrich Solowjow , Sebastian Trimpe

Leveraging offline data is a promising way to improve the sample efficiency of online reinforcement learning (RL). This paper expands the pool of usable data for offline-to-online RL by leveraging abundant non-curated data that is…

Machine Learning · Computer Science 2025-05-20 Yi Zhao , Aidan Scannell , Wenshuai Zhao , Yuxin Hou , Tianyu Cui , Le Chen , Dieter Büchler , Arno Solin , Juho Kannala , Joni Pajarinen

Offline reinforcement learning (offline RL) considers problems where learning is performed using only previously collected samples and is helpful for the settings in which collecting new data is costly or risky. In model-based offline RL,…

Machine Learning · Computer Science 2023-03-09 Mustafa O. Karabag , Ufuk Topcu

Model-based offline Reinforcement Learning (RL) constructs environment models from offline datasets to perform conservative policy optimization. Existing approaches focus on learning state transitions through ensemble models, rollouting…

Machine Learning · Computer Science 2025-03-27 Hongye Cao , Fan Feng , Jing Huo , Shangdong Yang , Meng Fang , Tianpei Yang , Yang Gao

We present an online model-based reinforcement learning algorithm suitable for controlling complex robotic systems directly in the real world. Unlike prevailing sim-to-real pipelines that rely on extensive offline simulation and model-free…

Robotics · Computer Science 2026-05-07 Fang Nan , Hao Ma , Qinghua Guan , Josie Hughes , Michael Muehlebach , Marco Hutter

In general class-incremental learning, researchers typically use sample sets as a tool to avoid catastrophic forgetting during continuous learning. At the same time, researchers have also noted the differences between class-incremental…

Machine Learning · Computer Science 2024-08-16 Weimin Yin , Bin Chen adn Chunzhao Xie , Zhenhao Tan

Model-based reinforcement learning (MBRL) offers an intuitive way to increase the sample efficiency of model-free RL methods by simultaneously training a world model that learns to predict the future. These models constitute the large…

Artificial Intelligence · Computer Science 2025-12-19 Ashish Sundar , Chunbo Luo , Xiaoyang Wang

While reinforcement learning (RL) methods that learn an internal model of the environment have the potential to be more sample efficient than their model-free counterparts, learning to model raw observations from high dimensional sensors…

Machine Learning · Computer Science 2023-06-27 Raj Ghugare , Homanga Bharadhwaj , Benjamin Eysenbach , Sergey Levine , Ruslan Salakhutdinov

Recent success in Deep Reinforcement Learning (DRL) methods has shown that policy optimization with respect to an off-policy distribution via importance sampling is effective for sample reuse. In this paper, we show that the use of…

Machine Learning · Computer Science 2023-02-07 Zichuan Lin , Xiapeng Wu , Mingfei Sun , Deheng Ye , Qiang Fu , Wei Yang , Wei Liu

Model-agnostic feature attributions can provide local insights in complex ML models. If the explanation is correct, a domain expert can validate and trust the model's decision. However, if it contradicts the expert's knowledge, related work…

Machine Learning · Computer Science 2023-06-30 Joran Michiels , Maarten De Vos , Johan Suykens

We propose a hybrid approach aimed at improving the sample efficiency in goal-directed reinforcement learning. We do this via a two-step mechanism where firstly, we approximate a model from Model-Free reinforcement learning. Then, we…

Machine Learning · Computer Science 2019-01-09 Shoubhik Debnath , Gaurav Sukhatme , Lantao Liu

Model-free reinforcement learning (RL) methods are succeeding in a growing number of tasks, aided by recent advances in deep learning. However, they tend to suffer from high sample complexity, which hinders their use in real-world domains.…

Machine Learning · Computer Science 2018-10-08 Thanard Kurutach , Ignasi Clavera , Yan Duan , Aviv Tamar , Pieter Abbeel

Score-based diffusion models are a powerful class of generative models, but their practical use often depends on training neural networks to approximate the score function. Training-free diffusion models provide an attractive alternative by…

Numerical Analysis · Mathematics 2026-01-28 Pengjun Wang , Zezhong Zhang , Minglei Yang , Feng Bao , Yanzhao Cao , Guannan Zhang