Embodied AI & Behavioral Modeling: From Unitree G1 to Smart Grid Optimization

Tue, 24 Mar 2026 00:00:00 +0000

Is it possible to “run” a behavioral economics model on a robot?

As I prepare for my new Mac Studio M4 Max (128GB) to arrive in May, my research is pivoting toward Embodied AI. This isn’t just about robotics; it’s about the micro-foundation of decision-making in autonomous systems.

1. The Idea: Behavioral Models as “Firmware”

Most robotics today focuses on perception and navigation. But what if we encode Behavioral Economics models (like prospect theory or hyperbolic discounting) directly into the decision logic of a robot?

Unitree G1 / XLeRobot: These platforms aren’t just toys. They are “embodied agents.”
The Experiment: If a robot has to choose between an immediate “low-energy” task and a delayed “high-reward” task, how does it weigh them? By implementing Behavioral Modeling, we can simulate how human-like biases might affect autonomous agents in complex environments.

2. The Princeton PPPP Connection: Smart Grids

This might sound like pure engineering, but it has profound implications for Energy Policy and Smart Grids:

Autonomous Energy Optimization: Future energy systems won’t be managed by humans in real-time. They will be managed by a mesh of autonomous agents—from smart thermostats to EV chargers.
Micro-Foundations: In energy modeling, we often assume these agents are “perfectly rational.” But what if they aren’t? By studying Embodied AI Behavioral Decision Logic, we can build more resilient energy models that account for “irrational” or “constrained” agent behavior in smart grids.
The Goal: Integrating these micro-level behavioral insights into the Peking-Princeton Project (PPPP) macro-energy models.

3. Future Academic Calendar: A New Chapter

As of today, March 24, 2026, I am at a crossroads. Tomorrow, March 25, marks the start of the UCSD Spring Quarter. This is the final sprint before my defense on April 14.

The transition from a “pure” behavioral economist to an “embodied AI” researcher mirrors the transition from a PhD student to a postdoc. The next few months will be dedicated to:

FODP: Finalizing my dissertation slides (aiming for 20+ slides by tomorrow).
Hardware Prep: Setting up the Mac Studio for local LLM and robotics simulation.
Princeton/Stanford Transition: Finalizing applications that bridge these two worlds.

This is the fourth installment in a series exploring the future of behavioral economics. The journey from Wuhan’s vaccination clinics to the autonomous grids of the future continues.

Intertemporal Choice & Hyperbolic Discounting: From Vaccines to Energy Policy

Tue, 24 Mar 2026 00:00:00 +0000

Individual decision-making often suffers from a fundamental conflict: The present self wants comfort, while the future self needs security.

This struggle, central to Intertemporal Choice, manifests in everything from public health to global energy transitions. At its heart lies Hyperbolic Discounting.

1. The Core Concept: Hyperbolic Discounting

In classical economics, we assume people discount the future at a constant, exponential rate. In reality, we are much more “present-biased.”

We overvalue immediate rewards and overstate immediate costs. This leads to a decision failure where we choose a smaller, sooner benefit (like avoiding a 30-minute queue or a small tax) over a much larger, later gain (like long-term immunity or a stable climate).

2. From Vaccination to Energy Policy

My recent research on Waiting Time as a Behavioral Barrier in vaccination shows how even a 3-month delay in protection leads to a “utility cliff.” This is a classic example of hyperbolic discounting: the short-term cost of waiting outweighs the massive long-term benefit of health.

But this model extends far beyond health. Consider Energy Policy:

The Problem: Energy transitions (like shifting to renewables or nuclear) are typical “current cost, future benefit” models.
The Bias: Implementing green energy requires significant upfront investment and potential short-term price hikes. The benefits—reduced emissions and energy independence—are decades away.
The Short-sighted Path: Because of hyperbolic discounting, both voters and policymakers tend to favor cheaper, fossil-fuel-based energy paths that provide immediate relief but catastrophic long-term costs.

3. The Princeton PPPP Connection

As I look toward the Peking-Princeton Project (PPPP) and related energy policy research at Princeton, my goal is to introduce these behavioral models into energy systems modeling.

By quantifying the “behavioral discount rate” of different demographics, we can design policies that “nudge” society toward long-term thinking. Whether it’s a vaccine or a power plant, the challenge remains the same: Helping our present selves make choices our future selves will thank us for.

This is the second installment in a series exploring the intersection of behavioral economics and public policy. Join me on April 14, 2026, for my PhD dissertation defense!

Princeton PPPP | Yichao Jin | Academic Blog