Multi-agent Double Deep Q-Networks

• Type: Article in International Conference Proceedings Book
• Date: 2017

Authors

Simoes, D (Author) Other; lau, n (Author) FCUP; reis, lp (Author) REIT

Conference proceedings International

Title: PROGRESS IN ARTIFICIAL INTELLIGENCE (EPIA 2017)

Pages: 123-134

18th EPIA Conference on Artificial Intelligence (EPIA)

Univ Porto, Fac Engn, Porto, PORTUGAL, SEP 05-08, 2017

Indexing

ISI Web of Knowledge - 1 Citation

Scopus - 3 Citations

Other information

Authenticus ID: P-00M-YK9

DOI: 10.1007/978-3-319-65340-2_11

Abstract (EN): There are many open issues and challenges in the multi-agent reward-based learning field. Theoretical convergence guarantees are lost, and the complexity of the action-space is also exponential to the amount of agents calculating their optimal joint-action. Function approximators, such as deep neural networks, have successfully been used in singleagent environments with high dimensional state-spaces. We propose the Multi-agent Double Deep Q-Networks algorithm, an extension of Deep Q-Networks to the multi-agent paradigm. Two common techniques of multi-agent Q-learning are used to formally describe our proposal, and are tested in a Foraging Task and a Pursuit Game. We also demonstrate how they can generalize to similar tasks and to larger teams, due to the strength of deep-learning techniques, and their viability for transfer learning approaches. With only a small fraction of the initial task's training, we adapt to longer tasks, and we accelerate the task completion by increasing the team size, thus empirically demonstrating a solution to the complexity issues of the multi-agent field.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 12