Abbas Abdolmaleki
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Abbas Abdolmaleki has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Luís Paulo Reis
Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal
3 shared publications - Nuno Lau
University of Aveiro
3 shared publications - Gerhard Neumann
Autonomous Learning Robots Lab, Karlsruhe Institute of Technology, Karlsruhe, Germany
2 shared publications David Simões
University of Aveiro
1 shared publication- David Simões
University of Aveiro
1 shared publication Gerhard Neumann
TU Darmstadt
1 shared publication
Latest Publications
- 8 January 2019
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 96 (2) , 141-157
Contextual Direct Policy Search
- 8 January 2019
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 96 (2) , 141-157
Contextual Direct Policy Search
- Open Access
Guide Actor-Critic for Continuous Control
Actor-critic methods solve reinforcement learning problems by updating a parameterized policy known as an actor in a direction that increases an estimate of the expected return known as a critic. However, existing actor-critic methods only use values or gradients of the critic to update the policy parameter. In this paper, we propose a novel actor-critic method called the guide actor-critic (GAC). GAC firstly learns a guide actor that locally maximizes the critic and then it updates the policy parameter based on the guide actor by supervised learning. Our main theoretical contributions are two folds. First, we show that GAC updates the guide actor by performing second-order optimization in the action space where the curvature matrix is based on the Hessians of the critic. Second, we show that the deterministic policy gradient method is a special case of GAC when the Hessians are ignored. Through experiments, we show that our method is a promising reinforcement learning method for continuous controls.
Open AccessGuide Actor-Critic for Continuous Control
Actor-critic methods solve reinforcement learning problems by updating a parameterized policy known as an actor in a direction that increases an estimate of the expected return known as a critic. However, existing actor-critic methods only use values or gradients of the critic to update the policy parameter. In this paper, we propose a novel actor-critic method called the guide actor-critic (GAC). GAC firstly learns a guide actor that locally maximizes the critic and then it updates the policy parameter based on the guide actor by supervised learning. Our main theoretical contributions are two folds. First, we show that GAC updates the guide actor by performing second-order optimization in the action space where the curvature matrix is based on the Hessians of the critic. Second, we show that the deterministic policy gradient method is a special case of GAC when the Hessians are ignored. Through experiments, we show that our method is a promising reinforcement learning method for continuous controls.
- 1 November 2017
- Published by Springer Nature
- p. 45-57
Learning a Humanoid Kick with Controlled Distance
- 1 November 2017
- Published by Springer Nature
- p. 45-57
Learning a Humanoid Kick with Controlled Distance
- 15 February 2016
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 83 (3-4) , 393-408
Contextual Policy Search for Linear and Nonlinear Generalization of a Humanoid Walking Controller
- 15 February 2016
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 83 (3-4) , 393-408
Contextual Policy Search for Linear and Nonlinear Generalization of a Humanoid Walking Controller