Papers with LGM-Zero
A Fairness-Driven Method for Learning Human-Compatible Negotiation Strategies (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in AI and NLP have led researchers to develop techniques to build autonomous agents which can achieve human-level performance in bargaining games such as Deal-orno-Deal. |
| Approach: | They propose a negotiation framework which incorporates fairness into reward design and search to learn human-compatible negotiation strategies. |
| Outcome: | The proposed framework achieves more egalitarian negotiation outcomes and improves negotiation quality. |