Marc Lanctot

sharky6000.bsky.social

30 May 2026 09:13

Heads up! I am excited to be presenting this paper @aamasconf.bsky.social this Friday May 29th at 14:00 Paphos time! Hope to see you there! 😁🙏

Marc Lanctot

sharky6000.bsky.social

13 May 2026 13:55

Ok #booksky, time to post about the third of the recent biographies: "The Infinity Machine: Demis Hassabis, DeepMind, and the Quest for Superintelligence". I ♥️ LOVED ♥️ this book! I've been recommending it to pretty much everyone who is curious to know about the history of Google DeepMind. 🧵 1/N

Marc Lanctot

sharky6000.bsky.social

18 March 2026 17:25

PSRO frames population-based training in mulitagent RL using game-theoretic foundations 👍 But, using RL to learn best response policies is very costly. So.. how about we use an LLM to produce response policies? 🤔 Joint work with Daniel Hennes, Zun Li, and John Schultz. arxiv.org/abs/2603.10098

Seth Karten

sethkarten.ai

14 March 2026 08:51

open.substack.com/pub/sethkart...

bidiptas13.bsky.social

21 November 2025 19:50

Introducing 🥚EGGROLL 🥚(Evolution Guided General Optimization via Low-rank Learning)! 🚀 Scaling backprop-free Evolution Strategies (ES) for billion-parameter models at large population sizes ⚡100x Training Throughput 🎯Fast Convergence 🔢Pure Int8 Pretraining of RNN LLMs