# Intention Inference Under Execution Noise: Separating Aleatoric and Epistemic Uncertainty in Social Dilemmas

arXiv: https://arxiv.org/abs/2608.02440 · HTML: https://mlsanity.com/paper/2608.02440/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 3 Aug 2026.

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

- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Learning with Opponent-Learning Awareness](https://mlsanity.com/paper/1709.04326/) (2017)
- [Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability](https://mlsanity.com/paper/2107.06277/) (2021)
- [Factorised Active Inference for Strategic Multi-Agent Interactions](https://mlsanity.com/paper/2411.07362/) (2024)
- [Properties of Winning Iterated Prisoner's Dilemma Strategies](https://mlsanity.com/paper/2001.05911/) (2020)
- [An analytical model of active inference in the Iterated Prisoner's Dilemma](https://mlsanity.com/paper/2306.15494/) (2023)

## Abstract (arXiv)

In noisy social dilemmas, intended actions are stochastically corrupted before execution, so an observed defection may reflect hostile intent or action error. Standard Markov Decision Process (MDP) formulations treat executed actions as states, structurally precluding this distinction and causing systematic over-retaliation. We introduce a Partially Observable MDP (POMDP) formulation encoding opponent intentions as latent states and executed actions as noisy observations, solved within the active inference (AIF) framework with a cost function that decomposes into epistemic and pragmatic components that jointly address inferring current intent and learning how intent evolves. In the Iterated Prisoner's Dilemma with symmetric noise, we derive a critical noise threshold governing cooperation collapse, connecting it to a fixed-point condition on learned priors. Experiments reveal that the value of intention inference is context-dependent: the POMDP provides consistent advantages against conditionally cooperative opponents, but mutual intention inference under sufficient noise produces correlated belief-driven collapse. The advantage is specific to games where intent attribution is decision-relevant.