Evolving Action Abstractionsfor Real-Time Planning in Extensive-Form Games

Julian Mariño

Rubens Moraes

Claudio Toledo

Levi H. S. Lelis

[0]

THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, pp. 2330-2337, 2019.

Cited by: 5|Views5

Abstract:

A key challenge for planning systems in real-time multi-agent domains is to search in large action spaces to decide an agent's next action. Previous works showed that handcrafted action abstractions allow planning systems to focus their search on a subset of promising actions. In this paper we show that the problem of generating action ab...More

Code:

Data:

Full Text

View via Publisher