# Inferring and Conveying Intentionality: Beyond Numerical Rewards to Logical Intentions

arXiv: https://arxiv.org/abs/2207.05058 · HTML: https://mlsanity.com/paper/2207.05058/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 23 references that are in the map.
- First posted on arXiv 6 Jul 2022.

## Builds on (most cited first, 3 of 3)

- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization](https://mlsanity.com/paper/1603.00448/) (2016)
- [Thinking Fast and Slow: Optimization Decomposition Across Timescales](https://mlsanity.com/paper/1704.07785/) (2017)

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

- [On Computational Mechanisms for Shared Intentionality, and Speculation on Rationality and Consciousness](https://mlsanity.com/paper/2306.13657/) (2023)

## Abstract (arXiv)

Shared intentionality is a critical component in developing conscious AI agents capable of collaboration, self-reflection, deliberation, and reasoning. We formulate inference of shared intentionality as an inverse reinforcement learning problem with logical reward specifications. We show how the approach can infer task descriptions from demonstrations. We also extend our approach to actively convey intentionality. We demonstrate the approach on a simple grid-world example.