English
Related papers

Related papers: Generalized Population-Based Training for Hyperpar…

200 papers

We present a simple, sample-efficient algorithm for introducing large but directed learning steps in reinforcement learning (RL), through the use of evolutionary operators. The methodology uses a population of RL agents training with a…

Neural and Evolutionary Computing · Computer Science 2023-05-15 Harshad Khadilkar

Reinforcement Learning (RL) can directly enhance the reasoning capabilities of large language models without extensive reliance on Supervised Fine-Tuning (SFT). In this work, we revisit the traditional Policy Gradient (PG) mechanism and…

Machine Learning · Computer Science 2026-02-04 Xiangxiang Chu , Hailang Huang , Xiao Zhang , Fei Wei , Yong Wang

The mathematical formula is the human language to describe nature and is the essence of scientific research. Finding mathematical formulas from observational data is a major demand of scientific research and a major challenge of artificial…

Machine Learning · Computer Science 2024-04-10 Yanjie Li , Weijun Li , Lina Yu , Min Wu , Jingyi Liu , Wenqiang Li , Meilan Hao , Shu Wei , Yusong Deng

Model-based Reinforcement Learning (MBRL) is a promising framework for learning control in a data-efficient manner. MBRL algorithms can be fairly complex due to the separate dynamics modeling and the subsequent planning algorithm, and as a…

Machine Learning · Computer Science 2021-03-01 Baohe Zhang , Raghu Rajan , Luis Pineda , Nathan Lambert , André Biedenkapp , Kurtland Chua , Frank Hutter , Roberto Calandra

We propose a genetic algorithm (GA) for hyperparameter optimization of artificial neural networks which includes chromosomal crossover as well as a decoupling of parameters (i.e., weights and biases) from hyperparameters (e.g., learning…

Neural and Evolutionary Computing · Computer Science 2019-01-15 Aaron Vose , Jacob Balma , Alex Heye , Alessandro Rigazzi , Charles Siegel , Diana Moise , Benjamin Robbins , Rangan Sukumar

Reinforcement Learning (RL) algorithms suffer from the dependency on accurately engineered reward functions to properly guide the learning agents to do the required tasks. Preference-based reinforcement learning (PbRL) addresses that by…

Artificial Intelligence · Computer Science 2024-08-23 Youssef Abdelkareem , Shady Shehata , Fakhri Karray

Varying data augmentation policies and regularization over the course of optimization has led to performance improvements over using fixed values. We show that population based training is a useful tool to continuously search those…

Computation and Language · Computer Science 2020-10-09 Daniel Haziza , Jérémy Rapin , Gabriel Synnaeve

In this paper, a new population-guided parallel learning scheme is proposed to enhance the performance of off-policy reinforcement learning (RL). In the proposed scheme, multiple identical learners with their own value-functions and…

Machine Learning · Computer Science 2020-01-10 Whiyoung Jung , Giseung Park , Youngchul Sung

Optimal setting of several hyper-parameters in machine learning algorithms is key to make the most of available data. To this aim, several methods such as evolutionary strategies, random search, Bayesian optimization and heuristic rules of…

Machine Learning · Computer Science 2021-12-16 Juan Cruz Barsce , Jorge A. Palombarini , Ernesto C. Martínez

In this work, our goal is to train agents that can coordinate with seen, unseen as well as human partners in a multi-agent communication environment involving natural language. Previous work using a single set of agents has shown great…

Machine Learning · Computer Science 2022-10-25 Abhinav Gupta , Marc Lanctot , Angeliki Lazaridou

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we…

We present Gradient Boosting Reinforcement Learning (GBRL), a framework that adapts the strengths of gradient boosting trees (GBT) to reinforcement learning (RL) tasks. While neural networks (NNs) have become the de facto choice for RL,…

Machine Learning · Computer Science 2025-10-21 Benjamin Fuhrer , Chen Tessler , Gal Dalal

Vision-Language-Action (VLA) models have shown great potential in general robotic decision-making tasks via imitation learning. However, the variable quality of training data often constrains the performance of these models. On the other…

Robotics · Computer Science 2025-05-13 Hongyin Zhang , Zifeng Zhuang , Han Zhao , Pengxiang Ding , Hongchao Lu , Donglin Wang

Gradient Boosted Decision Trees (GBDT) is a very successful ensemble learning algorithm widely used across a variety of applications. Recently, several variants of GBDT training algorithms and implementations have been designed and heavily…

Machine Learning · Computer Science 2019-06-27 Yu Shi , Jian Li , Zhize Li

The most successful methods such as ReLU transfer functions, batch normalization, Xavier initialization, dropout, learning rate decay, or dynamic optimizers, have become standards in the field due, particularly, to their ability to increase…

Machine Learning · Computer Science 2020-10-26 Yurika Sakai , Andrey Kormilitzin , Qiang Liu , Alejo Nevado-Holgado

We study the problem of training a Reinforcement Learning (RL) agent that is collaborative with humans without using any human data. Although such agents can be obtained through self-play training, they can suffer significantly from…

Artificial Intelligence · Computer Science 2022-06-28 Rui Zhao , Jinming Song , Yufeng Yuan , Hu Haifeng , Yang Gao , Yi Wu , Zhongqian Sun , Yang Wei

Generalizability of Reinforcement Learning (RL) agents (ability to perform on environments different from the ones they have been trained on) is a key problem as agents have the tendency to overfit to their training environments. In order…

Machine Learning · Computer Science 2025-11-26 Olivier Moulin , Vincent Francois-lavet , Paul Elbers , Mark Hoogendoorn

Hyperparameter optimization (HPO) plays a critical role in improving model performance. Transformer-based HPO methods have shown great potential; however, existing approaches rely heavily on large-scale historical optimization trajectories…

Machine Learning · Computer Science 2025-09-23 Haoxin Guo , Jiawen Pan , Weixin Zhai

Despite recent innovations in network architectures and loss functions, training RNNs to learn long-term dependencies remains difficult due to challenges with gradient-based optimisation methods. Inspired by the success of Deep…

Machine Learning · Statistics 2019-05-24 Bryan Lim , Stefan Zohren , Stephen Roberts

Zero-shot coordination(ZSC), a key challenge in multi-agent game theory, has become a hot topic in reinforcement learning (RL) research recently, especially in complex evolving games. It focuses on the generalization ability of agents,…

Machine Learning · Computer Science 2025-11-19 Bingyu Hui , Lebin Yu , Quanming Yao , Yunpeng Qu , Xudong Zhang , Jian Wang