chemSKI with tokens: world building and economy in the SKI universe

2023-06-01 · Marius Buliga

chemSKI with tokens is a confluent graph rewrite system where all rewrites are local, which moreover can be used to do SKI calculus reductions. The graph rewrites of chemSKI are made conservative by the use of tokens. We thus achieve several goals: conservative rewrites in a chemical style, a solution to the problem of new edge names in a distributed, decentralized graphical reduction and a new estimation of the cost of a combinatory calculus computation. This formalism can be used either as an artificial chemistry or as a model of a virtual decentralized machine which performs only local reductions. A programs repository and the same article with simulations are available at github at https://mbuliga.github.io/chemski/chemski-with-tokens.html

📄 PDF Abstract BibTeX arXiv:2306.00938

Code (1)

mbuliga/chemski 공식 구현

Big Data based Research on Mechanisms of Sharing Economy Restructuring the World

2020-01-24

Many researches have discussed the phenomenon and definition of sharing economy, but an understanding of sharing economy's reconstructions of the world remains elusive. We illustrate the mechanism of sharing economy's re…

SWE-Universe: Scale Real-World Verifiable Environments to Millions

2026-02-02 · Mouxiang Chen, Lei Zhang, Yunlong Feng, Xuwu Wang 외 arxiv

We propose SWE-Universe, a scalable and efficient framework for automatically constructing real-world software engineering (SWE) verifiable environments from GitHub pull requests (PRs). To overcome the prevalent challeng…

Reinforcement Learning

UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation

2026-07-06 · Mengmeng Liu, Diankun Zhang, Jiuming Liu, Jianfeng Cui 외 arxiv

World Action Models (WAMs) have shown strong potential for improving action generalization in autonomous driving by using future video prediction as dense supervision for scene dynamics and temporal causality. However, i…

Autonomous Driving Video Prediction Video Denoising

Universe Points Representation Learning for Partial Multi-Graph Matching

2022-12-01 · Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard

Many challenges from natural world can be formulated as a graph matching problem. Previous deep learning-based methods mainly consider a full two-graph matching setting. In this work, we study the more general partial ma…

Deep Learning Graph Matching Representation Learning

FinRL-Meta: A Universe of Near-Real Market Environments for Data-Driven Deep Reinforcement Learning in Quantitative Finance

2021-12-13 · Xiao-Yang Liu, Jingyang Rui, Jiechao Gao, Liuqing Yang 외

Deep reinforcement learning (DRL) has shown huge potentials in building financial market simulators recently. However, due to the highly complex and dynamic nature of real-world markets, raw historical financial data oft…

Deep Reinforcement Learning GPU reinforcement-learning Reinforcement Learning+1