# RecBayes: Recurrent Bayesian Ad Hoc Teamwork in Large Partially Observable Domains

arXiv: https://arxiv.org/abs/2506.15756 · HTML: https://mlsanity.com/paper/2506.15756/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 21 references that are in the map.
- First posted on arXiv 18 Jun 2025.

## Builds on (most cited first, 7 of 7)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [A General Learning Framework for Open Ad Hoc Teamwork Using Graph-based Policy Learning](https://mlsanity.com/paper/2210.05448/) (2022)
- [Centralized Training with Hybrid Execution in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2210.06274/) (2022)
- [Learning to Cooperate with Completely Unknown Teammates](https://mlsanity.com/paper/2205.03289/) (2022)
- [Making Friends in the Dark: Ad Hoc Teamwork Under Partial Observability](https://mlsanity.com/paper/2310.01439/) (2023)

## Abstract (arXiv)

This paper proposes RecBayes, a novel approach for ad hoc teamwork under partial observability, a setting where agents are deployed on-the-fly to environments where pre-existing teams operate, that never requires, at any stage, access to the states of the environment or the actions of its teammates. We show that by relying on a recurrent Bayesian classifier trained using past experiences, an ad hoc agent is effectively able to identify known teams and tasks being performed from observations alone. Unlike recent approaches such as PO-GPL (Gu et al., 2021) and FEAT (Rahman et al., 2023), that require at some stage fully observable states of the environment, actions of teammates, or both, or approaches such as ATPO (Ribeiro et al., 2023) that require the environments to be small enough to be tabularly modelled (Ribeiro et al., 2023), in their work up to 4.8K states and 1.7K observations, we show RecBayes is both able to handle arbitrarily large spaces while never relying on either states and teammates' actions. Our results in benchmark domains from the multi-agent systems literature, adapted for partial observability and scaled up to 1M states and 2^125 observations, show that RecBayes is effective at identifying known teams and tasks being performed from partial observations alone, and as a result, is able to assist the teams in solving the tasks effectively.