Prototype for automatic negotiating agent within the context of the Cognitive and Immersive Room
Covid-19 Update: Following the state and university guidelines, HUMAINE organizers have decided to host this year's competition online via a web browser instead of running it in the on-campus immersive environment. At some future date, if conditions safely permit, we may demonstrate some of the submitted agents in the immersive environment. This does not affect how participants write/submit their code for now.
Following ANAC guidance, we have extended our deadlines for participants to submit their code.
Participants will find details in our previous emails. Please contact us if you have more questions.
HUMAINE (HUman Multi-Agent Immersive NEgotiation) is a new ANAC (Automated Negotiating Agents Competition) league that will premiere at the International Joint Conference on Artificial Intelligence in Yokohama in July 2020.
In this competition, two competing agents negotiate with a human buyer who wishes to purchase various ingredients from which cakes and pancakes can be made. The agents are rendered as avatars on a display, and the human interacts with them by speaking (in English) and looking at the one with whom they wish to negotiate. The negotiation platform uses a Speech-to-Text service to render the audio into text and a head-pose estimation system to infer the addressee, and passes that information to each agent. Each agent must interpret the utterance, determine an appropriate negotiation act (such as a counteroffer, acceptance, or rejection) in light of the utterance and any other relevant context, and determine how best to render that act into an utterance and an accompanying gesture. Upon receiving this message from the agent and checking it for compliance with competition rules, the system causes the avatar to behave and speak as specified. The winning agent is the one that best maximizes its utility across multiple rounds of negotiation with various humans and other agents.
Determining the winner
The competition winner is determined by accumulating each agent’s utility across a set of 10-minute rounds during which it interacts with different humans and other competing agents. An agent’s utility is the difference between the price for which it sells ingredients and those ingredients’ production cost (which is generated randomly for each round). Human buyers have a utility function that is based upon the number of cakes and pancakes they can make given the ingredients they have purchased, and they are rewarded according to their ability to maximize their utility during the competition. Humans are thus incentivized to drive as hard a bargain as possible, without running the risk of failing to reach an agreement with at least one agent.
Although the agent winner is determined by accumulated utility, the fact that the contest involves humans suggests that the most effective agents will be those that combine algorithmic prowess with social skills (e.g.. being fun, pleasant, or subtly manipulative).
Winning agents will receive cash prizes, and winning humans will have their names announced at the conference. A prize will also be awarded to an agent that is judged to be most socially adept or engaging (regardless of its accumulated utility).
Registration
If you are interested in participating in the HUMAINE 2020 competition, register here by Sunday, March 8th, 2020. As the time for the competition approaches, you will be given various tools and opportunities for testing your agents. Further information about technical details will be provided in the near future.
Timeline
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
** We encourage you to submit papers to ACAN.
* ACAN is International Workshop on Agent-based Complex Automated Negotiations
Technical Details
Detailed technical documentation and specifics of the competition rules can be seen here — Link to document
Sample agents and other code can be seen here on GitHub — https://github.com/humaine-anac
Code and document are live, please keep checking the two links for the most updated information
Publications
Divekar, Rahul R., Xiangyang Mou, Lisha Chen, Maira Gatti De Bayser, Melina Alberio Guerra, and Hui Su. "Embodied conversational AI agents in a multi-modal multi-agent competitive dialogue." In Proceedings of the 28th International Joint Conference on Artificial Intelligence, pp. 6512-6514. AAAI Press, 2019. [Full Paper]
Frequently Asked Questions (FAQ)
We maintain a list of Frequently Asked Questions (FAQ) and answers in a live document. The document is updated as we get more questions from our participants. Please see the document here.
Organizers
- Rahul Divekar (divekr@rpi.edu)
- Jeffrey O. Kephart (kephart@us.ibm.com)
- Hui Su (huisuibmres@us.ibm.com)
- Maira Gatti de Bayser (mgdebayser@br.ibm.com)