# Belief and Truth in Hypothesised Behaviours

arXiv: https://arxiv.org/abs/1507.07688 · HTML: https://mlsanity.com/paper/1507.07688/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jul 2015.

## Built on by (most cited first, 21 of 21)

- [A Survey of Ad Hoc Teamwork Research](https://mlsanity.com/paper/2202.10450/) (2022)
- [Deep Interactive Bayesian Reinforcement Learning via Meta-Learning](https://mlsanity.com/paper/2101.03864/) (2021)
- [Generalization in Cooperative Multi-Agent Systems](https://mlsanity.com/paper/2202.00104/) (2022)
- [Generating Teammates for Training Robust Ad Hoc Teamwork Agents via Best-Response Diversity](https://mlsanity.com/paper/2207.14138/) (2022)
- [Addressing Inherent Uncertainty: Risk-Sensitive Behavior Generation for Automated Driving using Distributional Reinforcement Learning](https://mlsanity.com/paper/2102.03119/) (2021)
- [A General Learning Framework for Open Ad Hoc Teamwork Using Graph-based Policy Learning](https://mlsanity.com/paper/2210.05448/) (2022)
- [Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challenge](https://mlsanity.com/paper/2510.02557/) (2025)
- [Combining Tree-Search, Generative Models, and Nash Bargaining Concepts in Game-Theoretic Reinforcement Learning](https://mlsanity.com/paper/2302.00797/) (2023)
- [Factorised Active Inference for Strategic Multi-Agent Interactions](https://mlsanity.com/paper/2411.07362/) (2024)
- [Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)](https://mlsanity.com/paper/2505.17323/) (2025)
- [Unsupervised Partner Design Enables Robust Ad-hoc Teamwork](https://mlsanity.com/paper/2508.06336/) (2025)
- [Temporal Induced Self-Play for Stochastic Bayesian Games](https://mlsanity.com/paper/2108.09444/) (2021)
- [Few-Shot Teamwork](https://mlsanity.com/paper/2207.09300/) (2022)
- [Risk-Constrained Interactive Safety under Behavior Uncertainty for Autonomous Driving](https://mlsanity.com/paper/2102.03053/) (2021)
- [Constant-Memory Strategies in Stochastic Games: Best Responses and Equilibria](https://mlsanity.com/paper/2505.07008/) (2025)
- [Partner Capability Estimation for Task-Agnostic Adaptation in Ad-Hoc Teamwork](https://mlsanity.com/paper/2607.27177/) (2026)
- [Combining a Meta-Policy and Monte-Carlo Planning for Scalable Type-Based Reasoning in Partially Observable Environments](https://mlsanity.com/paper/2306.06067/) (2023)
- [Safe Exploitative Play with Untrusted Type Beliefs](https://mlsanity.com/paper/2411.07679/) (2024)
- [Bayesian Robust Financial Trading with Adversarial Synthetic Market Data](https://mlsanity.com/paper/2601.17008/) (2026)
- [Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling](https://mlsanity.com/paper/2605.12411/) (2026)
- [Smart Alone, Blind Together: Why Accuracy Fails to CertifyTheory of Mind in Multi-Agent Teams](https://mlsanity.com/paper/2610.19051/) (2026)

## Abstract (arXiv)

There is a long history in game theory on the topic of Bayesian or "rational" learning, in which each player maintains beliefs over a set of alternative behaviours, or types, for the other players. This idea has gained increasing interest in the artificial intelligence (AI) community, where it is used as a method to control a single agent in a system composed of multiple agents with unknown behaviours. The idea is to hypothesise a set of types, each specifying a possible behaviour for the other agents, and to plan our own actions with respect to those types which we believe are most likely, given the observed actions of the agents. The game theory literature studies this idea primarily in the context of equilibrium attainment. In contrast, many AI applications have a focus on task completion and payoff maximisation. With this perspective in mind, we identify and address a spectrum of questions pertaining to belief and truth in hypothesised types. We formulate three basic ways to incorporate evidence into posterior beliefs and show when the resulting beliefs are correct, and when they may fail to be correct. Moreover, we demonstrate that prior beliefs can have a significant impact on our ability to maximise payoffs in the long-term, and that they can be computed automatically with consistent performance effects. Furthermore, we analyse the conditions under which we are able complete our task optimally, despite inaccuracies in the hypothesised types. Finally, we show how the correctness of hypothesised types can be ascertained during the interaction via an automated statistical analysis.