English
Related papers

Related papers: Sample-efficient Cross-Entropy Method for Real-tim…

200 papers

Large language models (LLMs) have been garnering increasing attention in the recommendation community. Some studies have observed that LLMs, when fine-tuned by the cross-entropy (CE) loss with a full softmax, could achieve…

Information Retrieval · Computer Science 2024-08-27 Cong Xu , Zhangchi Zhu , Mo Yu , Jun Wang , Jianyong Wang , Wei Zhang

Sampling-based algorithms, such as Rapidly Exploring Random Trees (RRT) and its variants, have been used extensively for motion planning. Control barrier functions (CBFs) have been recently proposed to synthesize controllers for…

Robotics · Computer Science 2022-06-03 Ahmad Ahmad , Calin Belta , Roberto Tron

In recent years, deep reinforcement learning has been shown to be adept at solving sequential decision processes with high-dimensional state spaces such as in the Atari games. Many reinforcement learning problems, however, involve…

Machine Learning · Computer Science 2018-06-05 Yiming Zhang , Quan Ho Vuong , Kenny Song , Xiao-Yue Gong , Keith W. Ross

Neural networks are very effective when trained on large datasets for a large number of iterations. However, when they are trained on non-stationary streams of data and in an online fashion, their performance is reduced (1) by the online…

Machine Learning · Computer Science 2023-07-04 Albin Soutif--Cormerais , Antonio Carta , Joost Van de Weijer

In risk-averse reinforcement learning (RL), the goal is to optimize some risk measure of the returns. A risk measure often focuses on the worst returns out of the agent's experience. As a result, standard methods for risk-averse RL often…

Machine Learning · Computer Science 2022-10-13 Ido Greenberg , Yinlam Chow , Mohammad Ghavamzadeh , Shie Mannor

Deep reinforcement learning has shown remarkable success in the past few years. Highly complex sequential decision making problems from game playing and robotics have been solved with deep model-free methods. Unfortunately, the sample…

Machine Learning · Computer Science 2021-07-20 Aske Plaat , Walter Kosters , Mike Preuss

In multi-goal reinforcement learning with a sparse binary reward, training agents is particularly challenging, due to a lack of successful experiences. To solve this problem, hindsight experience replay (HER) generates successful…

Robotics · Computer Science 2024-01-11 Taeyoung Kim , Dongsoo Har

Sampling-based algorithms are widely used for motion planning in high-dimensional configuration spaces. However, due to low sampling efficiency, their performance often diminishes in complex configuration spaces with narrow corridors.…

Robotics · Computer Science 2025-07-22 Lu Huang , Lingxiao Meng , Jiankun Wang , Xingjian Jing

Beam search is a desirable choice of test-time decoding algorithm for neural sequence models because it potentially avoids search errors made by simpler greedy methods. However, typical cross entropy training procedures for these models do…

Machine Learning · Computer Science 2017-10-10 Kartik Goyal , Graham Neubig , Chris Dyer , Taylor Berg-Kirkpatrick

Leveraging planning during learning and decision-making is central to the long-term development of intelligent agents. Recent works have successfully combined tree-based search methods and self-play learning mechanisms to this end. However,…

Artificial Intelligence · Computer Science 2024-11-01 Matthew V Macfarlane , Edan Toledo , Donal Byrne , Paul Duckworth , Alexandre Laterre

Identifying algorithms that flexibly and efficiently discover temporally-extended multi-phase plans is an essential step for the advancement of robotics and model-based reinforcement learning. The core problem of long-range planning is…

Artificial Intelligence · Computer Science 2020-07-09 Aidan Curtis , Minjian Xin , Dilip Arumugam , Kevin Feigelis , Daniel Yamins

Efficient probabilistic inference by variable elimination in graphical models requires an optimal elimination order. However, finding an optimal order is a challenging combinatorial optimisation problem for models with a large number of…

Artificial Intelligence · Computer Science 2025-03-13 Sagad Hamid , Tanya Braun

Safe reinforcement learning (RL) is crucial for deploying RL agents in real-world applications, as it aims to maximize long-term rewards while satisfying safety constraints. However, safe RL often suffers from sample inefficiency, requiring…

Machine Learning · Computer Science 2024-06-03 Shangding Gu , Laixi Shi , Yuhao Ding , Alois Knoll , Costas Spanos , Adam Wierman , Ming Jin

Simplicity is a critical inductive bias for designing data-driven controllers, especially when robustness is important. Despite the impressive results of deep reinforcement learning in complex control tasks, it is prone to capturing…

Machine Learning · Computer Science 2025-05-09 Bang You , Chenxu Wang , Huaping Liu

Reinforcement learning (RL) algorithms for continuous control tasks require accurate sampling-based action selection. Many tasks, such as robotic manipulation, contain inherent problem symmetries. However, correctly incorporating symmetry…

Robotics · Computer Science 2024-12-18 Linfeng Zhao , Owen Howell , Xupeng Zhu , Jung Yeon Park , Zhewen Zhang , Robin Walters , Lawson L. S. Wong

Autonomously performing tasks often requires robots to plan high-level discrete actions and continuous low-level motions to realize them. Previous TAMP algorithms have focused mainly on computational performance, completeness, or optimality…

Robotics · Computer Science 2025-12-15 Andreu Matoses Gimenez , Nils Wilde , Chris Pek , Javier Alonso-Mora

Among the most prevalent motion planning techniques, sampling and trajectory optimization have emerged successful due to their ability to handle tight constraints and high-dimensional systems, respectively. However, limitations in sampling…

Robotics · Computer Science 2021-07-30 Kalyan Vasudev Alwala , Mustafa Mukadam

Cross-entropy (CE) is the default training loss for supervised classification, but its sample efficiency is limited when labels are scarce. Existing remedies primarily act on the data side, via augmentation, synthesis, or transfer from…

Machine Learning · Computer Science 2026-05-12 Qipeng Zhan , Zhuoping Zhou , Li Shen

As language models grow ever larger, so do their vocabularies. This has shifted the memory footprint of LLMs during training disproportionately to one single layer: the cross-entropy in the loss computation. Cross-entropy builds up a logit…

Machine Learning · Computer Science 2025-03-12 Erik Wijmans , Brody Huval , Alexander Hertzberg , Vladlen Koltun , Philipp Krähenbühl

Many Imitation and Reinforcement Learning approaches rely on the availability of expert-generated demonstrations for learning policies or value functions from data. Obtaining a reliable distribution of trajectories from motion planners is…

Robotics · Computer Science 2021-07-13 Alexander Lambert , Byron Boots