# The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents

arXiv: https://arxiv.org/abs/2201.00411 · HTML: https://mlsanity.com/paper/2201.00411/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 49 references that are in the map.
- First posted on arXiv 2 Jan 2022.

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Emergent Tool Use From Multi-Agent Autocurricula](https://mlsanity.com/paper/1909.07528/) (2019)
- [Emergence of Grounded Compositional Language in Multi-Agent Populations](https://mlsanity.com/paper/1703.04908/) (2017)
- [Embodied Intelligence via Learning and Evolution](https://mlsanity.com/paper/2102.02202/) (2021)
- [Playing FPS Games with Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05521/) (2016)
- [Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robots](https://mlsanity.com/paper/2111.01674/) (2021)
- [Reinforcement Learning for Improving Agent Design](https://mlsanity.com/paper/1810.03779/) (2018)
- [Jointly Learning to Construct and Control Agents using Deep Reinforcement Learning](https://mlsanity.com/paper/1801.01432/) (2018)
- [Neuroevolution of Self-Interpretable Agents](https://mlsanity.com/paper/2003.08165/) (2020)
- [Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design](https://mlsanity.com/paper/2110.03659/) (2021)
- [Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learning](https://mlsanity.com/paper/1911.06832/) (2019)
- [Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions](https://mlsanity.com/paper/1811.08067/) (2018)
- [Fit2Form: 3D Generative Model for Robot Gripper Form Design](https://mlsanity.com/paper/2011.06498/) (2020)
- [MorphEyes: Variable Baseline Stereo For Quadrotor Navigation](https://mlsanity.com/paper/2011.03077/) (2020)

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

- [CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation](https://mlsanity.com/paper/2203.10421/) (2022)
- [The Emergence of Complex Behavior in Large-Scale Ecological Environments](https://mlsanity.com/paper/2510.18221/) (2025)

## Abstract (arXiv)

The last few years have witnessed substantial progress in the field of embodied AI where artificial agents, mirroring biological counterparts, are now able to learn from interaction to accomplish complex tasks. Despite this success, biological organisms still hold one large advantage over these simulated agents: adaptation. While both living and simulated agents make decisions to achieve goals (strategy), biological organisms have evolved to understand their environment (sensing) and respond to it (physiology). The net gain of these factors depends on the environment, and organisms have adapted accordingly. For example, in a low vision aquatic environment some fish have evolved specific neurons which offer a predictable, but incredibly rapid, strategy to escape from predators. Mammals have lost these reactive systems, but they have a much larger fields of view and brain circuitry capable of understanding many future possibilities. While traditional embodied agents manipulate an environment to best achieve a goal, we argue for an introspective agent, which considers its own abilities in the context of its environment. We show that different environments yield vastly different optimal designs, and increasing long-term planning is often far less beneficial than other improvements, such as increased physical ability. We present these findings to broaden the definition of improvement in embodied AI passed increasingly complex models. Just as in nature, we hope to reframe strategy as one tool, among many, to succeed in an environment. Code is available at: https://github.com/sarahpratt/introspective.