Davide Borghi

Research Fellow | Multi-Agent Reinforcement Learning

[Stefano Mariani @stemarO_O]

**Researchers in AI, agent-based systems, and causal reasoning**, the 1st CLaRAMAS workshop will take place in May at AAMAS in Paphos, Cyprus :)
Co-organisers Mehdi Dastani, André Meyer-Vitali, and @JulienSiebert
Check out the welcome post ;) https://t.co/NdMav4t4X6

[Davide Borghi @daveborg_]

I agree 100%

[Joseph Suarez 🐡 @jsuarez]

I don't care if Karpathy is down on RL. He, Carmack, Ilya, and Alec Radford could all show up in person to tell me I'm wasting my time and I'd still keep doing it. Because damn it this tech is too cool not to exist.

[Stefano Mariani @stemarO_O]

First paper by @daveborg_ 😎

Learning to communicate applied to swarm intelligence with heterogeneous agents!

#discoli25 #dcossiot25 #marl #swarmintelligence #artificialpheromones

https://t.co/jaQq5TQ9A3

[Dimitris Papailiopoulos @DimitrisPapail]

GPT-4 "discovered" the same sorting algorithm as AlphaDev by removing "mov S P".

No RL needed. Can I publish this on nature?

here are the prompts I used https://t.co/FWAsE81lyq
(excuse my idiotic typos, but gpt4 doesn't mind anyways)

[Davide Borghi @daveborg_]

@fmolivato @DimitrisPapail 🤯🤯🤯

[Elon Musk @elonmusk]

The amount of solar energy received by Earth could power a civilization over 100 times larger than ours!

[Davide Borghi @daveborg_]

@alfcnz Thank you Alfredo, it was a pleasure to meet you! 😀