Policy Gradients with Parameter-Based Exploration for Control
Authors:
- 1 September 2008
- book chapter
- Published by Springer Nature
- p. 387-396
Abstract
No abstract availableKeywords
This publication has 6 references indexed in Scilit:
- Making a Robot Learn to Play Soccer Using Reward and PunishmentLecture Notes in Computer Science, 2007
- Evaluation of Policy Gradient Methods and Variants on the Cart-Pole Benchmark2007
- Policy Gradient Methods for Robotics2006
- Natural Actor-Critic2005
- Completely Derandomized Self-Adaptation in Evolution StrategiesEvolutionary Computation, 2001
- Biped dynamic walking using reinforcement learningRobotics and Autonomous Systems, 1997