Reinforcement learning for robot soccer

By Martin A. Riedmiller, Thomas Gabel, Roland Hafner, Sascha Lange. 2009

291 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Control and Systems Engineering, Reinforcement Learning, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Control and Systems Engineering

In Reinforcement Learning

In Robotics & Control

Citations in the corpus

Reinforcement learning in robotics: A survey (2013, methodology): “It used multi-layer perceptrons to learn various sub-tasks such as learning defenses, interception, position control, kicking, motor speed control, dribbling, and penalty shots (Hafner and Riedmiller, 2003; Riedmiller et al., 2009).”
Active learning of inverse models with intrinsically motivated goal exploration in robots (2013, positive): “One way to address this issue is to take inspiration infant’s motor exploration/babbling behavior, which has been argued to be teleological via introducing goals explicitly inside a task space and driving exploration at the level of these goals [71–74].”
Deep visual foresight for planning robot motion (2016, background): “Several works have used deep neural networks to process images and represent policies for robotic control, initially for driving tasks [15], [16], later for robotic soccer [17], and most recently for robotic grasping [18], [19] and manipulation [20].”
Increasing the Action Gap: New Operators for Reinforcement Learning (2015, background): “…and may be crucial for systems operating at a ﬁne time scale such as video games (Togelius et al. 2009; Bellemare et al. 2013), real-time markets (Jiang and Powell 2015), and robotic platforms (Riedmiller et al. 2009; Hoburg and Tedrake 2009; Deisenroth and Rasmussen 2011; Sutton et al. 2011).”
Deep Reinforcement Learning from Self-Play in Imperfect-Information Games (2016, background): “Games have a tradition of encouraging advances in artificial intelligence and machine learning (Samuel, 1959; Tesauro, 1995; Campbell et al., 2002; Riedmiller et al., 2009; Gelly et al., 2012; Bowling et al., 2015).”
Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play (2017, background): “, 2016), and in in multi-agent games such as RoboSoccer (Riedmiller et al., 2009).”
Batch Policy Learning under Constraints (2019, background): “, 2011), physical robotic soccer (Riedmiller et al., 2009), and cart-pole swingup (Riedmiller, 2005), and clinical treatment (Prasad et al.”
Emergent Coordination Through Competition (2019, background): “, 1997), including simulated leagues, which has been tackled with machine learning techniques (Riedmiller et al., 2009; MacAlpine & Stone, 2018) but not yet mastered by endto-end reinforcement learning.”
Time Reversal as Self-Supervision (2018, background): “Methods for robot control from visual inputs have been demonstrated on problems ranging from driving [4] to soccer [5].”
Consequentialist conditional cooperation in social dilemmas with imperfect information (2017, background): “, 2017a), multi-agent coordination problems (Lowe et al., 2017; Foerster et al., 2017b; Riedmiller et al., 2009; Tampuu et al., 2017; Peysakhovich & Lerer, 2017), and the emergence of language (Lazaridou et al.”
Learning concurrent motor skills in versatile solution spaces (2012, background): “A large number of skills have been learned by reinforcement learning (RL), including the game 'Ball-in-the-Cup' [1], the Peg-in- Hole task [2], robot soccer [6], walking [3] and jumping [4].”
Interpretable Policies for Reinforcement Learning by Genetic Programming (2017, unknown): “…involving neural networks (NNs) modeling either the state-action value function (Ried-miller, 2005a,b; Schneegaß, Udluft, and Martinetz, 2007a,b; Riedmiller, Gabel, Hafner, and Lange, 2009) or system dynamics (Bakker, 2004; Sch¨afer, 2008; Depeweg, Hern´andez-Lobato, Doshi-Velez, and Udluft,…”
Autonomous reinforcement learning on raw visual input data in a real world application (2012, background): “Making learning systems increasingly autonomous in the sense that they can not only autonomously learn to improve from their own experiences [1], [2], but furthermore achieve this by requiring less and less prior knowledge for their setup, is one of the promising future research directions in machin”
Deep Reinforcement Learning for Multiagent Systems: A Review of Challenges, Solutions, and Applications (2018, methodology): “[10] built a soccer robot team (2009); and Mulling et al.”
Learning model-free robot control by a Monte Carlo EM algorithm (2009, background): “Reinforcement Learning (RL) is a notable paradigm for robot control with several reported successes in recent years (Tedrake et al., 2005; Abbeel et al., 2007; Kober and Peters, 2009; Riedmiller et al., 2009; Martinez-Cantin et al., 2009).”
Particle swarm optimization for generating interpretable fuzzy reinforcement learning policies (2016, background): “Research from the past two decades [13, 25, 20, 9] suggests that such batch RL algorithms satisfy real-world system requirements, particularly when involving neural networks (NNs) modeling either the state-action value function [28, 29, 36, 35, 30] or system dynamics [1, 32, 6].”
Reinforcement learning in feedback control (2011, background): “2007a), learning of robot behaviours (Peters and Schaal 2006; El-Fakdi and Carreras 2008), control of soccer robots (Riedmiller et al. 2009), and engine control (Liu et al.”