At Datapalooza 2023, Sam presented Semiotic's latest research & practical applications of AI & data analytics in web3 and shared details about bringing high-performance SQL queries to The Graph!
Indexers in The Graph protocol use a DSL called Agora to map query shapes to prices. However, manually populating and updating Agora models for each query is a tedious task, and, as a consequence, most indexers default to a flat pricing model. We have created and deployed reinforcement learning agents for Indexers to automatically compete on pricing. This talk, given by Dr. Tomasz Kornuta, is focused on our development process and our study of the market effects of multiple competing pricing agents.
Indexers within The Graph Protocol are rewarded via an indexing reward. How can indexers optimize their allocations so as to maximize the reward they receive? In this video, Anirudh Patel and Hope Yen formalize that question in terms of a reward function and explain how convex optimization can be used to find a solution. They then demonstrate a new tool that automates the solution to the allocation optimization problem.
Alexis Asseman presents on our reinforcement learning agent used to automatically set prices for Indexers in The Graph protocol.
Presented at the WIMV 2022 Devconnect workshop. For future workshops, check out https://wimv.dev or follow https://twitter.com/wimvdev.
Presented at the WIMV 2022 Devconnect workshop. For future workshops, check out https://wimv.dev or follow https://twitter.com/wimvdev.