English
Related papers

Related papers: Accelerating Reinforcement Learning with a Directi…

200 papers

Unrolled computation graphs are prevalent throughout machine learning but present challenges to automatic differentiation (AD) gradient estimation methods when their loss functions exhibit extreme local sensitivtiy, discontinuity, or…

Neural and Evolutionary Computing · Computer Science 2023-12-12 Oscar Li , James Harrison , Jascha Sohl-Dickstein , Virginia Smith , Luke Metz

Reinforcement learning (RL) is currently a popular research topic in control engineering and has the potential to make its way to industrial and commercial applications. Corresponding RL controllers are trained in direct interaction with…

Machine Learning · Computer Science 2021-10-20 Maximilian Schenke , Oliver Wallscheid

We propose a new reinforcement learning (RL) formulation for training continuous-time score-based diffusion models for generative AI to generate samples that maximize reward functions while keeping the generated distributions close to the…

Machine Learning · Computer Science 2025-08-12 Xuefeng Gao , Jiale Zha , Xun Yu Zhou

The performance of a deep neural network is heavily dependent on its architecture and various neural architecture search strategies have been developed for automated network architecture design. Recently, evolutionary neural architecture…

Neural and Evolutionary Computing · Computer Science 2020-03-27 Haoyu Zhang , Yaochu Jin , Ran Cheng , Kuangrong Hao

This work provides an efficient sampling method for the covariance matrix adaptation evolution strategy (CMA-ES) in large-scale settings. In contract to the Gaussian sampling in CMA-ES, the proposed method generates mutation vectors from a…

Neural and Evolutionary Computing · Computer Science 2022-03-25 Xiaoyu He , Zibin Zheng , Yuren Zhou

Envisioned application areas for reinforcement learning (RL) include autonomous driving, precision agriculture, and finance, which all require RL agents to make decisions in the real world. A significant challenge hindering the adoption of…

Machine Learning · Computer Science 2025-01-20 Dominik Baumann , Erfaun Noorani , James Price , Ole Peters , Colm Connaughton , Thomas B. Schön

Reinforcement learning (RL) and Deep Reinforcement Learning (DRL), in particular, have the potential to disrupt and are already changing the way we interact with the world. One of the key indicators of their applicability is their ability…

Machine Learning · Computer Science 2024-08-20 Nikolai Rozanov

Often times in imitation learning (IL), the environment we collect expert demonstrations in and the environment we want to deploy our learned policy in aren't exactly the same (e.g. demonstrations collected in simulation but deployment in…

Neural and Evolutionary Computing · Computer Science 2024-06-19 Silvia Sapora , Gokul Swamy , Chris Lu , Yee Whye Teh , Jakob Nicolaus Foerster

Sample inefficiency is a long-lasting challenge in deep reinforcement learning (DRL). Despite dramatic improvements have been made, the problem is far from being solved and is especially challenging in environments with sparse or delayed…

Machine Learning · Computer Science 2025-06-17 Federico Malato , Ville Hautamaki

Model-free continuous control for robot navigation tasks using Deep Reinforcement Learning (DRL) that relies on noisy policies for exploration is sensitive to the density of rewards. In practice, robots are usually deployed in cluttered…

Robotics · Computer Science 2023-02-24 Mingyu Cai , Erfan Aasi , Calin Belta , Cristian-Ioan Vasile

Deep reinforcement learning (RL) has achieved great empirical successes in various domains. However, the large search space of neural networks requires a large amount of data, which makes the current RL algorithms not sample efficient.…

Machine Learning · Computer Science 2020-08-18 Qianli Shen , Yan Li , Haoming Jiang , Zhaoran Wang , Tuo Zhao

Standard reinforcement learning (RL) optimizes policies for reward but imposes few constraints on how decisions evolve over time. As a result, policies may achieve high performance while exhibiting temporally incoherent behavior such as…

Machine Learning · Computer Science 2026-04-24 Sukesh Subaharan

Data selection is designed to accelerate learning with preserved performance. To achieve this, a fundamental thought is to identify informative data samples with significant contributions to the training. In this work, we propose…

Machine Learning · Computer Science 2025-09-30 Ziheng Cheng , Zhong Li , Jiang Bian

Route planning is essential to mobile robot navigation problems. In recent years, deep reinforcement learning (DRL) has been applied to learning optimal planning policies in stochastic environments without prior knowledge. However, existing…

Robotics · Computer Science 2023-04-21 Xi Lin , Paul Szenher , John D. Martin , Brendan Englot

We propose a population-based Evolutionary Stochastic Gradient Descent (ESGD) framework for optimizing deep neural networks. ESGD combines SGD and gradient-free evolutionary algorithms as complementary algorithms in one framework in which…

Machine Learning · Computer Science 2018-10-17 Xiaodong Cui , Wei Zhang , Zoltán Tüske , Michael Picheny

Energy management systems (EMS) are becoming increasingly important in order to utilize the continuously growing curtailed renewable energy. Promising energy storage systems (ESS), such as batteries and green hydrogen should be employed to…

Machine Learning · Computer Science 2022-12-13 Dongju Kang , Doeun Kang , Sumin Hwangbo , Haider Niaz , Won Bo Lee , J. Jay Liu , Jonggeol Na

In this paper we analyze the qualitative differences between evolutionary strategies and reinforcement learning algorithms by focusing on two popular state-of-the-art algorithms: the OpenAI-ES evolutionary strategy and the Proximal Policy…

Artificial Intelligence · Computer Science 2022-05-17 Nicola Milano , Stefano Nolfi

In this work we show that Evolution Strategies (ES) are a viable method for learning non-differentiable parameters of large supervised models. ES are black-box optimization algorithms that estimate distributions of model parameters; however…

Neural and Evolutionary Computing · Computer Science 2019-06-10 Karel Lenc , Erich Elsen , Tom Schaul , Karen Simonyan

Reinforcement learning (RL) is always the preferred embodiment to construct the control strategy of complex tasks, like asymmetric assembly tasks. However, the convergence speed of reinforcement learning severely restricts its practical…

Machine Learning · Computer Science 2021-04-12 Yuhang Gai , Jiuming Guo , Dan Wu , Ken Chen

Crafting effective reward signals remains a central challenge in Reinforcement Learning (RL), especially for complex reasoning tasks. Existing automated reward optimization methods typically rely on derivative-free search heuristics that…

Artificial Intelligence · Computer Science 2026-05-14 Sitao Cheng , Tianle Li , Xuhan Huang , Xunjian Yin , Difan Zou