# facebookresearch/end-to-end-negotiator

Deal or No Deal? End-to-End Learning for Negotiation Dialogues

Repository: https://github.com/facebookresearch/end-to-end-negotiator
Canonical: https://ross.abutalabs.com/products/end-to-end-negotiator
Language: Python
License: NOASSERTION
License Family: other
Archived: true
Last push: 2020-05-04T03:59:17+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3368, "days_push": 2312, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1400, forks 278 (observed 2026-08-28T04:04:37.071144+00:00)

## What it is
A PyTorch research codebase from Facebook AI Research implementing end-to-end learning for negotiation dialogues, including models for hierarchical text generation and planning for strategic dialogue. It trains neural agents to negotiate in natural language via supervised learning, reinforcement learning self-play, and rollout-based planning, and ships with a dataset of 5,808 negotiation dialogues.

## Use cases
- train a neural network to negotiate in natural language
- reproduce the Deal or No Deal negotiation dialogue paper
- run reinforcement learning self-play between dialogue agents
- get a dataset of negotiation dialogues for dialogue research
- experiment with hierarchical text generation and planning for strategic dialogue

## When to choose
- you are researching negotiation dialogues, strategic dialogue, or dialogue-based RL and want the original reference implementation
- you need the accompanying negotiation dialogue dataset for experiments
- you want to study rollout-based planning combined with language generation in PyTorch

## When to avoid
- you need a production-ready chatbot or dialogue system for real applications
- you want a maintained library with recent PyTorch support - the code targets PyTorch 1.0 and has not been updated since 2020
- you need multi-turn open-domain conversation rather than item-division negotiation

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, nlp, reinforcement-learning, chatbot
- domain: deep-learning, artificial-intelligence
- platform: python
- tags: pytorch, negotiation-dialogue, dialogue-systems, research-code, self-play, facebook-ai-research, dataset, natural-language-processing, research, linux, gpu

## Member repositories
- facebookresearch/end-to-end-negotiator (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:37.071144+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:39:06.442790+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/end-to-end-negotiator (fetched 2026-08-28T04:04:37.071144+00:00, sha f241e2b4bfc7)
- Data as of 2026-08-30T08:39:29.467469+00:00.