Self-Play Learning Task

A Self-Play Learning Task is an game learning task that is a unsupervised learning task.

• AKA: Playing Alone.
• See: Supervised Game Learning.

---

---

References

2016

• (Silver et al., 2016) ⇒ David Silver, Aja Huang, Chris J. Maddison, Arthur Guez, Laurent Sifre, George van den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, Sander Dieleman, Dominik Grewe, John Nham, Nal Kalchbrenner, Ilya Sutskever, Timothy Lillicrap, Madeleine Leach, Koray Kavukcuoglu, Thore Graepel, and Demis Hassabis. (2016). “Mastering the Game of Go with Deep Neural Networks and Tree Search.” In: Nature, 529(7587). doi:10.1038/nature16961

2009

• http://www.parents.com/toddlers-preschoolers/development/friendship/playing-alone/

2002

• (Bowling & Veloso, 2002) ⇒ Michael Bowling, and Manuela Veloso. (2002). “Multiagent Learning Using a Variable Learning Rate." Artificial Intelligence 136, no. 2

1996

• (Tesauro, 1994) ⇒ Gerald Tesauro. (1994). “TD-Gammon, a Self-teaching Backgammon Program, Achieves Master-level Play." Neural computation 6, no. 2

---