# Making Friends in the Dark: Ad Hoc Teamwork Under Partial Observability

arXiv: https://arxiv.org/abs/2310.01439 · HTML: https://mlsanity.com/paper/2310.01439/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 28 references that are in the map.
- First posted on arXiv 30 Sep 2023.

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

- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [On the Utility of Learning about Humans for Human-AI Coordination](https://mlsanity.com/paper/1910.05789/) (2019)
- ["Other-Play" for Zero-Shot Coordination](https://mlsanity.com/paper/2003.02979/) (2020)
- [A New Formalism, Method and Open Issues for Zero-Shot Coordination](https://mlsanity.com/paper/2106.06613/) (2021)
- [Quasi-Equivalence Discovery for Zero-Shot Emergent Communication](https://mlsanity.com/paper/2103.08067/) (2021)
- [Few-Shot Teamwork](https://mlsanity.com/paper/2207.09300/) (2022)

## Built on by (most cited first, 1 of 1)

- [RecBayes: Recurrent Bayesian Ad Hoc Teamwork in Large Partially Observable Domains](https://mlsanity.com/paper/2506.15756/) (2025)

## Abstract (arXiv)

This paper introduces a formal definition of the setting of ad hoc teamwork under partial observability and proposes a first-principled model-based approach which relies only on prior knowledge and partial observations of the environment in order to perform ad hoc teamwork. We make three distinct assumptions that set it apart previous works, namely: i) the state of the environment is always partially observable, ii) the actions of the teammates are always unavailable to the ad hoc agent and iii) the ad hoc agent has no access to a reward signal which could be used to learn the task from scratch. Our results in 70 POMDPs from 11 domains show that our approach is not only effective in assisting unknown teammates in solving unknown tasks but is also robust in scaling to more challenging problems.