https://derekwang2002.github.io/ai-intelligence/en/projects/ataraxos/ Material changes in AI models, agents, engineering and infrastructure, with primary sources and recommendations. en Mon, 02 Nov 2026 16:56:00 GMT https://derekwang2002.github.io/ai-intelligence/en/events/ev-20260930-03/ ev-20260930-03-published Sun, 04 Oct 2026 16:02:19 GMT New WATCH <p>Ataraxos combines dynamically damped self-play reinforcement learning with decision-time search for hidden-information games. It beat Pim Niemeijer 15–1 with four draws and went 38–2 at the 2025 Stratego World Championship. Training and belief-model code are public, but pretrained checkpoints are not.</p><p>Recommendation: WATCH</p><p>Sources: <a href="https://www.nature.com/articles/s41586-026-11036-y">Ataraxos plays Stratego</a> · <a href="https://news.mit.edu/2026/game-playing-ai-stratego-new-champ-0930">MIT: Ataraxos Stratego result</a> · <a href="https://github.com/AtaraxosAI/stratego">Ataraxos Stratego code</a></p>