English
Related papers

Related papers: Evolutionary Stochastic Policy Distillation

200 papers

Evolution strategy (ES) has been shown great promise in many challenging reinforcement learning (RL) tasks, rivaling other state-of-the-art deep RL methods. Yet, there are two limitations in the current ES practice that may hinder its…

Machine Learning · Computer Science 2020-02-24 Jiaxing Zhang , Hoang Tran , Guannan Zhang

Reinforcement learning for control over continuous spaces typically uses high-entropy stochastic policies, such as Gaussian distributions, for local exploration and estimating policy gradient to optimize performance. Many robotic control…

Machine Learning · Computer Science 2024-04-03 Ya-Chien Chang , Sicun Gao

Evolution Strategy (ES) is a powerful black-box optimization technique based on the idea of natural evolution. In each of its iterations, a key step entails ranking candidate solutions based on some fitness score. For an ES method in…

Machine Learning · Computer Science 2023-02-22 Eshwar S R , Shishir Kolathaya , Gugan Thoppe

Evolutionary algorithms have been used to evolve a population of actors to generate diverse experiences for training reinforcement learning agents, which helps to tackle the temporal credit assignment problem and improves the exploration…

Neural and Evolutionary Computing · Computer Science 2023-04-21 Chengpeng Hu , Jiyuan Pei , Jialin Liu , Xin Yao

Evolution Strategies (ES) are a powerful class of blackbox optimization techniques that recently became a competitive alternative to state-of-the-art policy gradient (PG) algorithms for reinforcement learning (RL). We propose a new method…

Neural and Evolutionary Computing · Computer Science 2020-03-16 Yunhao Tang , Krzysztof Choromanski , Alp Kucukelbir

Reinforcement learning for large language models faces a fundamental trade-off between sample efficiency and asymptotic performance: strictly on-policy methods discard trajectories after a single update, while off-policy reuse introduces…

Machine Learning · Computer Science 2026-05-26 Changyu Chen , Xiting Wang , Rui Yan

There is now significant historical data available on decision making in organizations, consisting of the decision problem, what decisions were made, and how desirable the outcomes were. Using this data, it is possible to learn a surrogate…

Neural and Evolutionary Computing · Computer Science 2020-04-23 Olivier Francon , Santiago Gonzalez , Babak Hodjat , Elliot Meyerson , Risto Miikkulainen , Xin Qiu , Hormoz Shahrzad

On-policy distillation has recently emerged as a promising alternative to standard sequence-level imitation, training a student by scoring its own rollouts with a teacher model. However, we observe ``Off-policy Teacher Decay'' problem in…

Machine Learning · Computer Science 2026-05-27 Zhou Ziheng , Jiaqi Li , Huacong Tang , Ying Nian Wu , Demetri Terzopoulos

Evolutionary strategies have recently been shown to achieve competing levels of performance for complex optimization problems in reinforcement learning. In such problems, one often needs to optimize an objective function subject to a set of…

Neural and Evolutionary Computing · Computer Science 2022-02-23 Youssef Diouane , Aurelien Lucchi , Vihang Patil

In this paper, we propose a novel meta-learning method in a reinforcement learning setting, based on evolution strategies (ES), exploration in parameter space and deterministic policy gradients. ES methods are easy to parallelize, which is…

Machine Learning · Computer Science 2019-05-09 Yiming Shen , Kehan Yang , Yufeng Yuan , Simon Cheng Liu

In recent years, Evolutionary Strategies were actively explored in robotic tasks for policy search as they provide a simpler alternative to reinforcement learning algorithms. However, this class of algorithms is often claimed to be…

Robotics · Computer Science 2021-11-10 Vladislav Kurenkov , Bulat Maksudov

We explore the use of Evolution Strategies (ES), a class of black box optimization algorithms, as an alternative to popular MDP-based RL techniques such as Q-learning and Policy Gradients. Experiments on MuJoCo and Atari show that ES is a…

Machine Learning · Statistics 2017-09-11 Tim Salimans , Jonathan Ho , Xi Chen , Szymon Sidor , Ilya Sutskever

Reinforcement learning (RL) has been successfully applied to solve the problem of finding obstacle-free paths for autonomous agents operating in stochastic and uncertain environments. However, when the underlying stochastic dynamics of the…

Machine Learning · Computer Science 2024-10-29 Sheryl Paul , Jyotirmoy V. Deshmukh

We propose expected policy gradients (EPG), which unify stochastic policy gradients (SPG) and deterministic policy gradients (DPG) for reinforcement learning. Inspired by expected sarsa, EPG integrates across the action when estimating the…

Machine Learning · Statistics 2018-04-17 Kamil Ciosek , Shimon Whiteson

Evolution Strategies (ES) is a class of powerful black-box optimisation methods that are highly parallelisable and can handle non-differentiable and noisy objectives. However, na\"ive ES becomes prohibitively expensive at scale on GPUs due…

Evolutionary Algorithms (EAs) and Deep Reinforcement Learning (DRL) have recently been integrated to take the advantage of the both methods for better exploration and exploitation.The evolutionary part in these hybrid methods maintains a…

Neural and Evolutionary Computing · Computer Science 2022-09-19 Yan Ma , Tianxing Liu , Bingsheng Wei , Yi Liu , Kang Xu , Wei Li

We propose expected policy gradients (EPG), which unify stochastic policy gradients (SPG) and deterministic policy gradients (DPG) for reinforcement learning. Inspired by expected sarsa, EPG integrates (or sums) across actions when…

Machine Learning · Statistics 2020-05-05 Kamil Ciosek , Shimon Whiteson

In this paper, we try to improve exploration in Blackbox methods, particularly Evolution strategies (ES), when applied to Reinforcement Learning (RL) problems where intermediate waypoints/subgoals are available. Since Evolutionary…

Robotics · Computer Science 2023-07-04 Kiran Lekkala , Laurent Itti

Consider learning a policy purely on the basis of demonstrated behavior -- that is, with no access to reinforcement signals, no knowledge of transition dynamics, and no further interaction with the environment. This *strictly batch…

Machine Learning · Statistics 2021-01-15 Daniel Jarrett , Ioana Bica , Mihaela van der Schaar

A key challenge in reinforcement learning (RL) is managing the exploration-exploitation trade-off without sacrificing sample efficiency. Policy gradient (PG) methods excel in exploitation through fine-grained, gradient-based optimization…

Machine Learning · Computer Science 2025-04-18 Zelal Su "Lain" Mustafaoglu , Keshav Pingali , Risto Miikkulainen
‹ Prev 1 2 3 10 Next ›