Systems4
- Agora-2A multi‑agent world model that enables multiple participants—human or AI—to share and interact within the same world simulation in real‑time.
- Odyssey-3A foundation world model for physical AI applications.
- PROWL-2A reinforcement‑learning framework where a team of agents and its world model each learn from their own curriculum in a single training loop.
- Starchild-1A multimodal world model.
Newest unveiled first. Systems that belong to a government program link to the program page, where variants, costs and contracts are.
Sources6
Profile3
- 1CompanyOdyssey
Odyssey · Supports Organization · description, Organization · name, Organization · website
“Odyssey-3 draws on a learned understanding of physics, motion, and cause-and-effect to act in physical and virtual worlds. One foundation world model powers policies for robots, humanoids, cars, drones, video games, and more”
- 2Companyodyssey-world-models website
Supports Organization · linkedin url
“https://www.linkedin.com/company/odysseyml/”
- 3
Sixth-Domain · Supports Organization · kind
“{"group": "startups", "id": "55ddee43-7044-43e7-8b85-64a9b9268c99", "name": "Odyssey"}”
Systems3
- 4
Odyssey · Supports System
“Odyssey-3 is a foundation world model that can power robots, drive cars, train AIs, pilot drones, and even play video games”
- 5
Odyssey · Supports System
“Agora-2 A multi-agent world model, enabling multiple participants—human or AI—to share and interact within the same world simulation in real-time”
- 6
Odyssey · Supports System
“Starchild-1 A step beyond world models that learn only from visual observation, toward systems that learn from richer multimodal interaction with the world”
Each fact on this page is attached to the sources that support it. Archived copies are linked when we keep one.