Search Results for "ai model"

NitroGen is a foundation model for generalist gaming agents developed under the MineDojo initiative, aimed at training a vision­-action AI that can play and interact with a wide variety of games by taking pixel inputs and predicting gamepad actions. As an open research model, NitroGen is trained on extensive gameplay data spanning thousands of hours and hundreds of games to instill broad, generalizable gaming competency rather than skill at a single title.

The project is the codebase for an AI agent named Cicero developed by Facebook Research. It is designed to play the board game Diplomacy by combining open-domain natural language negotiation with strategic planning. The repository includes training code, model checkpoints, and infrastructure for both language modelling (via the ParlAI framework) and reinforcement learning for strategy agents.

...RETRO represents an important step toward combining large-scale language modeling with information retrieval, offering researchers a foundation to study hybrid approaches for scaling AI responsibly.