Skip to Main content Skip to Navigation
Conference papers

Designing a Reinforcement Learning-based Adaptive AI for Large-Scale Strategy Games

Charles Madeira 1 Vincent Corruble 2 Geber Ramalho
1 ACASA - Agents Cognitifs et Apprentissage Symbolique Automatique
LIP6 - Laboratoire d'Informatique de Paris 6
2 SMA - Systèmes Multi-Agents
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : This paper investigates the challenges posed by the application of reinforcement learning to large-scale strategy games. In this context, we present steps and techniques which synthesize new ideas with state-of-the-art techniques from several areas of machine learning in a novel integrated learning approach for this kind of games. The performance of the approach is demonstrated on the task of learning valuable game strategies for a commercial wargame.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01351276
Contributor : Lip6 Publications <>
Submitted on : Wednesday, August 3, 2016 - 11:27:30 AM
Last modification on : Thursday, March 21, 2019 - 2:17:03 PM

Identifiers

  • HAL Id : hal-01351276, version 1

Citation

Charles Madeira, Vincent Corruble, Geber Ramalho. Designing a Reinforcement Learning-based Adaptive AI for Large-Scale Strategy Games. AAAI conference on Artificial Intelligence and Interactive Digital Entertainement, Jun 2006, Marina del Rey, California, United States. pp.121-123. ⟨hal-01351276⟩

Share

Metrics

Record views

67