Reinforcement learning agents providing advice in complex video games

Autor: Lisa Torrey, Matthew D. Taylor, Nicholas Carboni, Anestis Fachantidis, Ioannis Vlahavas
Rok vydání: 2014
Předmět:
Zdroj: Connection Science. 26:45-63
ISSN: 1360-0494
0954-0091
DOI: 10.1080/09540091.2014.885279
Popis: This article introduces a teacher–student framework for reinforcement learning, synthesising and extending material that appeared in conference proceedings [Torrey, L., & Taylor, M. E. (2013)]. Teaching on a budget: Agents advising agents in reinforcement learning. {Proceedings of the international conference on autonomous agents and multiagent systems}] and in a non-archival workshop paper [Carboni, N., &Taylor, M. E. (2013, May)]. Preliminary results for 1 vs. 1 tactics in StarCraft. {Proceedings of the adaptive and learning agents workshop (at AAMAS-13)}]. In this framework, a teacher agent instructs a student agent by suggesting actions the student should take as it learns. However, the teacher may only give such advice a limited number of times. We present several novel algorithms that teachers can use to budget their advice effectively, and we evaluate them in two complex video games: StarCraft and Pac-Man. Our results show that the same amount of advice, given at different moments, can have differe...
Databáze: OpenAIRE
Nepřihlášeným uživatelům se plný text nezobrazuje