# On the Origins of Self-Modeling

arXiv: https://arxiv.org/abs/2209.02010 · HTML: https://mlsanity.com/paper/2209.02010/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 5 Sep 2022.

## Builds on (most cited first, 10 of 10)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [Model-Based Reinforcement Learning for Atari](https://mlsanity.com/paper/1903.00374/) (2019)
- [Emergence of Locomotion Behaviours in Rich Environments](https://mlsanity.com/paper/1707.02286/) (2017)
- [Imagination-Augmented Agents for Deep Reinforcement Learning](https://mlsanity.com/paper/1707.06203/) (2017)
- [Recurrent Environment Simulators](https://mlsanity.com/paper/1704.02254/) (2017)
- [Learning Awareness Models](https://mlsanity.com/paper/1804.06318/) (2018)
- [Policy Optimization with Model-based Explorations](https://mlsanity.com/paper/1811.07350/) (2018)

## Built on by (most cited first, 2 of 2)

- [Teaching Robots to Build Simulations of Themselves](https://mlsanity.com/paper/2311.12151/) (2023)
- [Can Neural Networks Learn by Experimenting on Themselves? Self-Interventional Learning from Functional Consequences to Predictive Self-Knowledge](https://mlsanity.com/paper/2608.14894/) (2026)

## Abstract (arXiv)

Self-Modeling is the process by which an agent, such as an animal or machine, learns to create a predictive model of its own dynamics. Once captured, this self-model can then allow the agent to plan and evaluate various potential behaviors internally using the self-model, rather than using costly physical experimentation. Here, we quantify the benefits of such self-modeling against the complexity of the robot. We find a R2 =0.90 correlation between the number of degrees of freedom a robot has, and the added value of self-modeling as compared to a direct learning baseline. This result may help motivate self modeling in increasingly complex robotic systems, as well as shed light on the origins of self-modeling, and ultimately self-awareness, in animals and humans.