Download
End-to-End Negotiator is a PyTorch-based research framework developed by Facebook AI Research to train neural agents capable of conducting strategic negotiations in natural language. The project implements the models presented in two key papers: “Deal or No Deal? End-to-End Learning for Negotiation Dialogues” and “Hierarchical Text Generation and Planning for Strategic Dialogue”. It enables agents to plan, reason, and communicate effectively to maximize outcomes in multi-turn negotiations over shared resources. The framework provides code for both supervised learning (training from human dialogue data) and reinforcement learning (via self-play and rollout-based planning). It introduces a hierarchical latent model, where high-level intents are first clustered and then translated into coherent language, improving dialogue diversity and goal consistency. The repository also includes the Negotiate dataset, comprising over 5,800 dialogues across 2,200 unique scenarios.
Features
- Trains neural agents for natural language negotiation and decision-making
- Includes supervised and reinforcement learning with self-play capability
- Implements hierarchical intent-based planning for dialogue generation
- Provides multiple model architectures: baseline RNN, latent clustering, and full hierarchical models
- Bundled with a negotiation dialogue dataset of 5,800 human-collected examples
- Tools for simulating agent-vs-agent negotiations and analyzing negotiation outcomes
Project Samples
