A comprehensive autonomous decentralized systems framework for AI control architects.

Heterogeneous Hierarchical Multi Agent Reinforcement Learning for Air Combat

Computation lab

Clean, documented implementations of PPO-based algorithms for cooperative multi-agent reinforcement learning, focusing on SMAC environments. Features MLP and RNN-based MAPPO and HAPPO with various techniques.

Sample code for computing the Aiyagari (1994) model in CUDA (GPU). Hope it is useful for those interested in parallelizing quantitative macroeconomics models.

Analysis and implementation of a modified training environment from the paper "Imitation Learning over Heterogeneous Agents with Restraining Bolts." (De Giacomo et al, 2020)

Material for my Master Thesis | Summer Term 2023 | University of Bonn

Journal of Math Econ (2024)

EMINN implementation of Krusell-Smith model with neural network solutions.

Heterogeneous Households: Individual Agent Dynamics in AI-Driven Labor Markets (SFC-ABM)

Code for solving quantitative models in economics

PanCode is a fast open-source runtime for autonomous multi-agent workflows. Each agent in the fleet runs its own model and provider, shares context through a registry, and operates within configurable safety constraints. Multi-model. Multi-provider. Self-evolving. Built on Bun.

Codes related to the computational experiments of the working paper "Wang, Zhongli, Heterogeneous Consumers, Firm Competition and the Data Value Chain: An Agent-based Approach (April 23, 2025). Available at SSRN: https://ssrn.com/abstract=5235196 or http://dx.doi.org/10.2139/ssrn.5235196".