English
Related papers

Related papers: Evolutionary Stochastic Policy Distillation

200 papers

Deep Reinforcement Learning (RL) has emerged as a powerful method for addressing complex control problems, particularly those involving underactuated robotic systems. However, in some cases, policies may require refinement to achieve…

Robotics · Computer Science 2025-07-15 Marco Calì , Alberto Sinigaglia , Niccolò Turcato , Ruggero Carli , Gian Antonio Susto

Deep reinforcement learning (DRL) algorithms and evolution strategies (ES) have been applied to various tasks, showing excellent performances. These have the opposite properties, with DRL having good sample efficiency and poor stability,…

Machine Learning · Computer Science 2021-04-06 Kyunghyun Lee , Byeong-Uk Lee , Ukcheol Shin , In So Kweon

In constrained reinforcement learning (C-RL), an agent seeks to learn from the environment a policy that maximizes the expected cumulative reward while satisfying minimum requirements in secondary cumulative reward constraints. Several…

Machine Learning · Computer Science 2022-12-06 Tianqi Zheng , Pengcheng You , Enrique Mallada

Evolution Strategies (ES) emerged as a scalable alternative to popular Reinforcement Learning (RL) techniques, providing an almost perfect speedup when distributed across hundreds of CPU cores thanks to a reduced communication overhead.…

Machine Learning · Statistics 2018-11-13 Víctor Campos , Xavier Giro-i-Nieto , Jordi Torres

Evolutionary Strategies (ES) are a popular family of black-box zeroth-order optimization algorithms which rely on search distributions to efficiently optimize a large variety of objective functions. This paper investigates the potential…

Neural and Evolutionary Computing · Computer Science 2019-02-01 Louis Faury , Clement Calauzenes , Olivier Fercoq , Syrine Krichen

Reinforcement learning from verifiable rewards (RLVR) suffers from sparse outcome signals, creating severe exploration bottlenecks on complex reasoning tasks. Recent on-policy self-distillation methods attempt to address this by utilizing…

Machine Learning · Computer Science 2026-05-20 Yang Li , Erik Nijkamp , Semih Yavuz , Shafiq Joty

Deep Reinforcement Learning (DRL) algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically suffer from three core difficulties: temporal credit assignment with sparse rewards, lack…

Machine Learning · Computer Science 2018-10-30 Shauharda Khadka , Kagan Tumer

We propose a new method for training an agent via an evolutionary strategy (ES), in which we iteratively improve a set of samples to imitate: Starting with a random set, in every iteration we replace a subset of the samples with samples…

Neural and Evolutionary Computing · Computer Science 2020-09-18 Roy Eliya , J. Michael Herrmann

Recently, Pareto Set Learning (PSL) has been proposed for learning the entire Pareto set using a neural network. PSL employs preference vectors to scalarize multiple objectives, facilitating the learning of mappings from preference vectors…

Neural and Evolutionary Computing · Computer Science 2024-04-15 Rongguang Ye , Longcan Chen , Jinyuan Zhang , Hisao Ishibuchi

Evolution Strategies (ES) have emerged as a scalable gradient-free alternative to reinforcement learning based LLM fine-tuning, but it remains unclear whether comparable task performance implies comparable solutions in parameter space. We…

Machine Learning · Computer Science 2026-04-03 William Hoy , Binxu Wang , Xu Pan

Diffusion distillation, exemplified by Distribution Matching Distillation (DMD), has shown great promise in few-step generation but often sacrifices quality for sampling speed. While integrating Reinforcement Learning (RL) into distillation…

Machine Learning · Computer Science 2026-04-22 Linwei Dong , Ruoyu Guo , Ge Bai , Zehuan Yuan , Yawei Luo , Changqing Zou

Evolution Strategies (ES) has recently emerged as a competitive alternative to reinforcement learning (RL) for large language model (LLM) fine-tuning, offering advantages through simplicity, scalability, and inference-only training.…

Machine Learning · Computer Science 2026-05-29 Kajetan Schweighofer , Conor F. Hayes , Roberto Dailey , Risto Miikkulainen , Xin Qiu

On-policy distillation is an efficient alternative to reinforcement learning, offering dense token-level training signals. However, its reliance on a stronger external teacher has driven recent work on on-policy self-distillation, where the…

Machine Learning · Computer Science 2026-05-07 Xin Yu , Liuchen Liao , Yiwen Zhang , Yingchen Yu , Lingzhou Xue , Qinzhen Guo

We consider the problem of online reinforcement learning for the Stochastic Shortest Path (SSP) problem modeled as an unknown MDP with an absorbing state. We propose PSRL-SSP, a simple posterior sampling-based reinforcement learning…

Machine Learning · Computer Science 2021-06-11 Mehdi Jafarnia-Jahromi , Liyu Chen , Rahul Jain , Haipeng Luo

Policy gradient reinforcement learning (RL) algorithms have achieved impressive performance in challenging learning tasks such as continuous control, but suffer from high sample complexity. Experience replay is a commonly used approach to…

Machine Learning · Statistics 2020-02-19 Saad Mohamad , Giovanni Montana

Large language model post-training relies on reinforcement learning to improve model capability and alignment quality. However, the off-policy training paradigm introduces distribution shift, which often pushes the policy beyond the trust…

Machine Learning · Computer Science 2026-04-24 Zhenpeng Su , Leiyu Pan , Minxuan Lv , Tiehua Mei , Zijia Lin , Yuntao Li , Wenping Hu , Ruiming Tang , Kun Gai , Guorui Zhou

Efficient exploration is a central problem in reinforcement learning and is often formalized as maximizing the entropy of the state-action occupancy measure. While unconstrained maximum-entropy exploration is relatively well understood,…

Machine Learning · Computer Science 2026-05-01 Florian Wolf , Ilyas Fatkhullin , Niao He

Evolution Strategy (ES) algorithms have shown promising results in training complex robotic control policies due to their massive parallelism capability, simple implementation, effective parameter-space exploration, and fast training time.…

Robotics · Computer Science 2022-07-28 Kuang-Huei Lee , Ofir Nachum , Tingnan Zhang , Sergio Guadarrama , Jie Tan , Wenhao Yu

In this work we propose a novel data-driven, real-time power system voltage control method based on the physics-informed guided meta evolutionary strategy (ES). The main objective is to quickly provide an adaptive control strategy to…

Systems and Control · Electrical Eng. & Systems 2021-11-30 Yan Du , Qiuhua Huang , Renke Huang , Tianzhixi Yin , Jie Tan , Wenhao Yu , Xinya Li

Planning is a powerful approach to reinforcement learning with several desirable properties. However, it requires a model of the world, which is not readily available in many real-life problems. In this paper, we propose to learn a world…

Machine Learning · Computer Science 2020-11-24 Thor V. A. N. Olesen , Dennis T. T. Nguyen , Rasmus Berg Palm , Sebastian Risi