# Knowledge-based and Data-driven Reasoning and Learning for Ad Hoc Teamwork

arXiv: https://arxiv.org/abs/2208.11556 · HTML: https://mlsanity.com/paper/2208.11556/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 29 references that are in the map.
- First posted on arXiv 24 Aug 2022.

## Builds on (most cited first, 6 of 6)

- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Explainable Planning](https://mlsanity.com/paper/1709.10256/) (2017)
- [Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning](https://mlsanity.com/paper/2006.10412/) (2020)
- [Deep Interactive Bayesian Reinforcement Learning via Meta-Learning](https://mlsanity.com/paper/2101.03864/) (2021)
- [Natural Emergence of Heterogeneous Strategies in Artificially Intelligent Competitive Teams](https://mlsanity.com/paper/2007.03102/) (2020)
- [REBA: A Refinement-Based Architecture for Knowledge Representation and Reasoning in Robotics](https://mlsanity.com/paper/1508.03891/) (2015)

## Abstract (arXiv)

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.