Agent Coordination in Air Combat Simulation using Multi-Agent Deep Reinforcement Learning
Autor: | Fredrik Heintz, Johan Källström |
---|---|
Rok vydání: | 2020 |
Předmět: |
Computer Sciences
Computer science Multi-agent system Air combat ComputerApplications_COMPUTERSINOTHERSYSTEMS 02 engineering and technology Construct (python library) 010501 environmental sciences computer.software_genre 01 natural sciences Task (project management) Domain (software engineering) Intelligent agent agent-based modeling intelligent agents machine learning multi-agent systems Datavetenskap (datalogi) Human–computer interaction 0202 electrical engineering electronic engineering information engineering Reinforcement learning State space 020201 artificial intelligence & image processing computer 0105 earth and related environmental sciences |
Zdroj: | SMC |
Popis: | Simulation-based training has the potential to significantly improve training value in the air combat domain. However, synthetic opponents must be controlled by high-quality behavior models, in order to exhibit human-like behavior. Building such models by hand is recognized as a very challenging task. In this work, we study how multi-agent deep reinforcement learning can be used to construct behavior models for synthetic pilots in air combat simulation. We empirically evaluate a number of approaches in two air combat scenarios, and demonstrate that curriculum learning is a promising approach for handling the high-dimensional state space of the air combat domain, and that multi-objective learning can produce synthetic agents with diverse characteristics, which can stimulate human pilots in training. Funding: Swedish Governmental Agency for Innovation SystemsVinnova [NFFP7/2017-04885]; Wallenberg Artificial Intelligence, Autonomous Systems and Software Program (WASP) - Knut and Alice Wallenberg Foundation |
Databáze: | OpenAIRE |
Externí odkaz: |