Pluto reaches StarCraft II strength with pure self-play, no human imitation — unlike AlphaStar
TimDarcet · x · 2026-10-08
Tim Darcet clarifies a key distinction: AlphaStar was not pure self-play and relied heavily on imitation learning, whereas Pluto's impressive feat is that it learned StarCraft II entirely without human data, using self-play alone. The point underscores how hard it is to reach strong play without human demonstrations.
More from Research
- 1-gram wireless mesoscope images cortex-wide activity in freely moving mice — KordingLab · 2026-10-23
- Reversible computing veteran poses open problem: universal BARCS primitives from unbiased Josephson junctions — MikePFrank · 2026-10-23
- Arc Institute uses genomic language model to map 376M prokaryotic noncoding sequences into 5.14M clusters — tedgreenwald · 2026-10-23
- The rise of AI-assisted peer review: reviewers are making it into the appendix — abursuc · 2026-10-23
- Anthropic uses Claude to formally verify security properties in 100+ open-source libraries at RISC-V assembly level — AnthropicAI · 2026-10-23
- Researchers test 9 strategies to pick LLM teams, beating random selection by up to 36.1% — shangbinfeng · 2026-10-23