AI Chat AI Image Generator AI Video Text to Speech

Policy Search in Continuous Action Domains: an Overview

03/13/2018

∙

by Olivier Sigaud, et al.

∙

∙

Continuous action policy search, the search for efficient policies in continuous control tasks, is currently the focus of intensive research driven both by the recent success of deep reinforcement learning algorithms and by the emergence of competitors based on evolutionary algorithms. In this paper, we present a broad survey of policy search methods, incorporating into a common big picture these very different approaches as well as alternatives such as Bayesian Optimization and directed exploration methods. The main message of this overview is in the relationship between the families of methods, but we also outline some factors underlying sample efficiency properties of the various approaches. Besides, to keep this survey as short and didactic as possible, we do not go into the details of mathematical derivations of the elementary algorithms.

Olivier Sigaud
39 publications
Freek Stulp
9 publications

page 1

page 2

page 3

page 4

research

∙ 01/31/2017

Deep Reinforcement Learning for Robotic Manipulation-The state of the art

The focus of this work is to enumerate the various approaches and algori...

0 Smruti Amarjyoti, et al. ∙

research

∙ 11/30/2017

Comparing Deep Reinforcement Learning and Evolutionary Methods in Continuous Control

Reinforcement learning and evolutionary strategy are two major approache...

0 Shangtong Zhang, et al. ∙

research

∙ 01/12/2022

Evolutionary Action Selection for Gradient-based Policy Learning

Evolutionary Algorithms (EAs) and Deep Reinforcement Learning (DRL) have...

9 Yan Ma, et al. ∙

research

∙ 02/14/2018

GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms

In continuous action domains, standard deep reinforcement learning algor...

0 Cédric Colas, et al. ∙

research

∙ 09/24/2020

Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey

Deep reinforcement learning has recently seen huge success across multip...

0 Wenshuai Zhao, et al. ∙

research

∙ 03/27/2019

Autoregressive Policies for Continuous Control Deep Reinforcement Learning

Reinforcement learning algorithms rely on exploration to discover new be...

0 Dmytro Korenkevych, et al. ∙

research

∙ 05/22/2019

COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration

Data efficiency and robustness to task-irrelevant perturbations are long...

12 Nicholas Watters, et al. ∙