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

by   Sarah Pratt, et al.
University of Washington

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:


DANLI: Deliberative Agent for Following Natural Language Instructions

Recent years have seen an increasing amount of work on embodied AI agent...

What do navigation agents learn about their environment?

Today's state of the art visual navigation agents typically consist of l...

ToriLLE: Learning Environment for Hand-to-Hand Combat

We present Toribash Learning Environment (ToriLLE), an interface with vi...

Reasoning in Highly Reactive Environments

The aim of my Ph.D. thesis concerns Reasoning in Highly Reactive Environ...

Modeling Social Interaction for Baby in Simulated Environment for Developmental Robotics

Task-specific AI agents are showing remarkable performance across differ...

AllenAct: A Framework for Embodied AI Research

The domain of Embodied AI, in which agents learn to complete tasks throu...

Please sign up or login with your details

Forgot password? Click here to reset