Evolving Keepaway Soccer Players through Task Decomposition

By Shimon Whiteson, Nate Kohl, Risto Miikkulainen, Peter Stone. 2003

112 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Developmental and Educational Psychology, Economics and Econometrics

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

1. Shimon Whiteson
2. J. Urgen Schmidhuber
3. Peter Stone
4. Matthew E. Taylor
5. Sergey Levine
6. Pieter Abbeel
7. Faustino J. Gomez
8. Risto Miikkulainen

In Developmental and Educational Psychology

1. J. Urgen Schmidhuber
2. Shimon Whiteson
3. Faustino J. Gomez
4. Risto Miikkulainen
5. Peter Stone

In Economics and Econometrics

1. J. Urgen Schmidhuber
2. Shimon Whiteson
3. Faustino J. Gomez
4. Risto Miikkulainen
5. Peter Stone
6. Matthew E. Taylor
7. Matthew J. Hausknecht

Citations in the corpus

• Deep learning in neural networks: An overview (2014, methodology): “Numerous alternative HRL techniques have been proposed (e.g., Ring, 1991, 1994; Jameson, 1991; Tenenberg et al., 1993; Moore and Atkeson, 1995; Precup et al., 1998; Dietterich, 2000b; Menache et al., 2002; Doya et al., 2002; Ghavamzadeh and Mahadevan, 2003; Barto and Mahadevan, 2003; Samejima et al.”
• On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, methodology): “In principle, this can be done through incremental NN evolution [70], hierarchical NN evolution [306, 285], hierarchical Policy Gradient algorithms [63], or asymptotically optimal ways of algorithmic transfer learning [238].”
• One Big Net For Everything (2018, methodology): “…profit from this prior knowledge, learning a new task through additional weight changes more quickly than learning the task from scratch, e.g., [17, 100, 13], ideally through optimal algorithmic transfer learning , like in the at least asymptotically Optimal Ordered Problem Solver [69], where new…”
• Robust non-linear control through neuroevolution (2003, background): “2002), developing cooperative strategies in robotic soccer (Whiteson et al. 2003), and evolving adaptive agent teams (Bryant and Miikkulainen 2003).”
• Evolutionary Computation for Reinforcement Learning (2012, methodology): “For example, in the task of robot soccer keepaway, domain knowledge has been used to decompose the task into different components, each representing an important skill such as running towards the ball or getting open for a pass (Whiteson et al, 2005).”
• Neuroevolutionary reinforcement learning for generalized helicopter control (2009, background): “Given its numerous successes in noisy, continuous control problems [8, 9, 13, 17, 23, 24], neuroevolution is well-suited to this task.”
• Keepaway Soccer: From Machine Learning Testbed to Benchmark (2005, methodology): “[21] used neuroevolution to train keepers in the SoccerBots domain [3], an extension of the more abstract TeamBots simulator [2].”
• Accelerated Neural Evolution through Cooperatively Coevolved Synapses (2008, methodology): “…algorithm that has been a applied successfully to many domains (Perez- Bergquist, 2001; Lubberts and Miikkulainen, 2001; Greer et al., 2002; Whiteson et al., 2003; Bryant and Miikkulainen, 2003; Gomez et al., 2001; Grasemann and Miikkulainen, 2005), including the real world reinforcement…”
• A Survey and Analysis of Multi-Robot Coordination (2013, unknown): “Other relevant works on MRTD include [106].”