Deal or No Deal? End-to-End Learning for Negotiation Dialogues
This work addresses the challenge of semi-cooperative dialogue for AI, with potential applications in automated negotiation systems, though it is incremental in advancing end-to-end learning for specific tasks.
The paper tackled the problem of training AI agents for negotiation dialogues by introducing an end-to-end learning approach that learns linguistic and reasoning skills without annotated dialogue states, using a new dataset of human-human negotiations and a dialogue rollout technique that improved performance.
Much of human dialogue occurs in semi-cooperative settings, where agents with different goals attempt to agree on common decisions. Negotiations require complex communication and reasoning skills, but success is easy to measure, making this an interesting task for AI. We gather a large dataset of human-human negotiations on a multi-issue bargaining task, where agents who cannot observe each other's reward functions must reach an agreement (or a deal) via natural language dialogue. For the first time, we show it is possible to train end-to-end models for negotiation, which must learn both linguistic and reasoning skills with no annotated dialogue states. We also introduce dialogue rollouts, in which the model plans ahead by simulating possible complete continuations of the conversation, and find that this technique dramatically improves performance. Our code and dataset are publicly available (https://github.com/facebookresearch/end-to-end-negotiator).