Download
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. It supports two variants: Cicero (which handles full “press” negotiation) and Diplodocus (a variant focused on no-press diplomacy) as described in the README. The codebase is implemented primarily in Python with performance-critical components in C++ (via pybind11 bindings) and is configured to run in a high‐GPU cluster environment. Configuration is managed via protobuf files to define tasks such as self-play, benchmark agent comparisons, and RL training. The project is now archived and read-only, reflecting that it is no longer actively developed but remains publicly available for research use.
Features
- Implements Cicero, the first AI to achieve human-level Diplomacy play with strategic dialogue
- Combines large language modeling with deep reinforcement learning and planning
- Includes code for both full-press (dialogue) and no-press (non-dialogue) Diplomacy agents
- Uses ParlAI for language understanding and generation and custom RL for game strategy
- Provides tools for simulating games, benchmarking, and visualizing game progress
- Includes extensive configs, pre-trained models, and modular test frameworks
Project Samples
