Knowledge-based and Data-driven Reasoning and Learning for Ad Hoc Teamwork
This work addresses the challenge of practical ad hoc teamwork in domains with limited training data, though it appears incremental as it builds on existing methods by integrating logical reasoning.
The authors tackled the problem of ad hoc teamwork where agents collaborate without prior coordination by developing an architecture that combines knowledge-based reasoning with data-driven learning. Their approach demonstrated better performance than a data-driven baseline in the Fort Attack benchmark, supporting adaptation to unforeseen changes and incremental learning from limited samples.
We present an architecture for ad hoc teamwork, which refers to collaboration in a team of agents without prior coordination. State of the art methods for this problem often include a data-driven component that uses a long history of prior observations to model the behaviour of other agents (or agent types) and to determine the ad hoc agent's behaviour. In many practical domains, it is challenging to find large training datasets, and necessary to understand and incrementally extend the existing models to account for changes in team composition or domain attributes. Our architecture combines the principles of knowledge-based and data-driven reasoning and learning. Specifically, we enable an ad hoc agent to perform non-monotonic logical reasoning with prior commonsense domain knowledge and incrementally-updated simple predictive models of other agents' behaviour. We use the benchmark simulated multi-agent collaboration domain Fort Attack to demonstrate that our architecture supports adaptation to unforeseen changes, incremental learning and revision of models of other agents' behaviour from limited samples, transparency in the ad hoc agent's decision making, and better performance than a data-driven baseline.