Applied Worlds

Simulation,
World Models
& Environment
Dynamics.

Original, evidence-first research on how environments evolve, how to simulate them faithfully, and how agents learn and decide inside worlds they can never fully model.

Thread I — World Models Thread II — Agent Dynamics Thread III — Counterfactual Launching 2026
The Question
How do we build computational representations of complex environments that are good enough to learn from, plan with, and make decisions in — when the real environment is non-stationary, partially observable, and changes because agents are acting inside it?
  • 01World Models
  • 02Agent-Environment Dynamics
  • 03Counterfactual Simulation
At a Glance Overview
Focus
Simulation, World Models & Environment Dynamics
Research Threads
Three — World Models, Agent Dynamics, Counterfactual Simulation
Standard
Hypothesis → Experiment → Honest Record
Release Pattern
Experiments when done. No schedule. No calendar pressure.
Research Threads Three
01
Thread I

World Models

Learning environment dynamics from observation. How do you learn a latent representation of how a system evolves over time? How do you dream in that latent space to plan without acting in the real world? Builds on a control engineering foundation — state-space models, dynamical systems, stability analysis — reimagined through modern deep learning and physics-informed neural networks.

Latent Dynamics Physics-Informed ML Ha & Schmidhuber State-Space Models Model-Based Planning
02
Thread II

Agent-Environment Dynamics

What happens when agents act inside an environment and the environment changes as a result? In markets, it is reflexivity. In multi-agent RL, it is non-stationarity — every agent's policy is part of every other agent's environment. In social systems, it is the Lucas critique. Experiments involve building simulated environments with multiple adaptive agents and studying what emerges from the feedback loop.

Reflexivity Multi-Agent RL Non-Stationarity Lucas Critique Emergence Causal Inference
03
Thread III

Counterfactual Simulation

Using simulation to answer "what if?" Structural causal models as simulable world models. The experiments involve building environments where you can intervene, not just observe, and measuring whether counterfactual reasoning actually improves decision-making compared to purely observational methods.

Counterfactuals Structural Causal Models Do-Calculus Intervention Decision Quality
What Gets Published Artifact types
Thread I
Learned Dynamics

Training dynamics models, evaluating fidelity, testing model-based planning inside dream environments.

Thread II
Multi-Agent Studies

Building simulated environments with adaptive agents and documenting what emerges from the interaction.

Thread III
Counterfactual Reasoning

Causal simulation versus purely observational methods. Does intervening improve decision quality?

Across Threads
Physics-Informed ML

Hybrid models combining known dynamics with learned components. Environment design studies.

Editorial Boundary What this is not
No Learning Notes Not passive study output. If it is not an original experiment, it does not ship.
No Reposting No paper summaries, no blog recaps. Only direct implementation and measurement.
No Tutorials Not an educational resource. Every artifact begins with a hypothesis.
Failures Included Negative results are published alongside successes. The record is the product.
Keep Moving Progress over optics. Completeness over calendar pressure.
Artifact Index All published work
Title Type Thread Status Published

First experiments arriving 2026