# Perspective Taking in Deep Reinforcement Learning Agents

arXiv: https://arxiv.org/abs/1907.01851 · HTML: https://mlsanity.com/paper/1907.01851/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2019.

## Built on by (most cited first, 7 of 7)

- [Mind the gap: Challenges of deep learning approaches to Theory of Mind](https://mlsanity.com/paper/2203.16540/) (2022)
- [Visual Perspective Taking for Opponent Behavior Modeling](https://mlsanity.com/paper/2105.05145/) (2021)
- [Emergence of Adaptive Circadian Rhythms in Deep Reinforcement Learning](https://mlsanity.com/paper/2307.12143/) (2023)
- [How well can LLMs provide planning feedback in grounded environments?](https://mlsanity.com/paper/2509.09790/) (2025)
- [Latent Emission-Augmented Perspective-Taking (LEAPT) for Human-Robot Interaction](https://mlsanity.com/paper/2308.06498/) (2023)
- [The Observer-Situation Lattice: A Unified Formal Basis for Perspective-Aware Cognition](https://mlsanity.com/paper/2603.01407/) (2026)
- [Beyond the Cartesian Illusion: Testing Two-Stage Multi-Modal Theory of Mind under Perceptual Bottlenecks](https://mlsanity.com/paper/2605.18194/) (2026)

## Abstract (arXiv)

Perspective taking is the ability to take the point of view of another agent. This skill is not unique to humans as it is also displayed by other animals like chimpanzees. It is an essential ability for social interactions, including efficient cooperation, competition, and communication. Here we present our progress toward building artificial agents with such abilities. We implemented a perspective taking task inspired by experiments done with chimpanzees. We show that agents controlled by artificial neural networks can learn via reinforcement learning to pass simple tests that require perspective taking capabilities. We studied whether this ability is more readily learned by agents with information encoded in allocentric or egocentric form for both their visual perception and motor actions. We believe that, in the long run, building better artificial agents with perspective taking ability can help us develop artificial intelligence that is more human-like and easier to communicate with.