The latest from Odyssey

The latest from Odyssey

Thoughts, experiments, and progress from the Odyssey team

Thoughts, experiments, and progress from the Odyssey team

World Model

Odyssey-3

Our most powerful foundation world model yet, materially advancing the state-of-the-art in physical accuracy of world models

World Model

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

Reinforcement Learning

PROWL-2

PROWL-2 is the first framework in which a team of agents and its world model each learn from their own curriculum, continually and within a single training loop

World Model

Starchild-1

A step beyond world models that learn only from visual observation, toward systems that learn from richer multimodal interaction with the world

Information

World Models

World Model

Odyssey-3

Our most powerful foundation world model yet, materially advancing the state-of-the-art in physical accuracy of world models

World Model

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

Reinforcement Learning

PROWL-2

PROWL-2 is the first framework in which a team of agents and its world model each learn from their own curriculum, continually and within a single training loop

World Model

Starchild-1

A step beyond world models that learn only from visual observation, toward systems that learn from richer multimodal interaction with the world

Information

World Models

World Model

Odyssey-3

Our most powerful foundation world model yet, materially advancing the state-of-the-art in physical accuracy of world models

World Model

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

Reinforcement Learning

PROWL-2

PROWL-2 is the first framework in which a team of agents and its world model each learn from their own curriculum, continually and within a single training loop

World Model

Starchild-1

A step beyond world models that learn only from visual observation, toward systems that learn from richer multimodal interaction with the world

Information

World Models

World Model

Odyssey-3

Our most powerful foundation world model yet, materially advancing the state-of-the-art in physical accuracy of world models

World Model

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

Reinforcement Learning

PROWL-2

PROWL-2 is the first framework in which a team of agents and its world model each learn from their own curriculum, continually and within a single training loop

World Model

Starchild-1

A step beyond world models that learn only from visual observation, toward systems that learn from richer multimodal interaction with the world

Information

World Models