The Challenge of Negotiation in the Game of Diplomacy

The game of Diplomacy has been used as a test case for complex automated negotiations for a long time, but to date very few successful negotiation algorithms have been implemented for this game. We have therefore decided to include a Diplomacy tournament within the annual Automated Negotiating Agents Competition (ANAC). In this paper we present the setup and the results of the ANAC 2017 Diplomacy Competition and the ANAC 2018 Diplomacy Challenge. We observe that none of the negotiation algorithms submitted to these two editions have been able to significantly improve the performance over a non-negotiating baseline agent. We analyze these algorithms and discuss why it is so hard to write successful negotiation algorithms for Diplomacy. Finally, we provide experimental evidence that, despite these results, coalition formation and coordination do form essential elements of the game.

[1]  Catholijn M. Jonker,et al.  ANAC 2017: Repeated Multilateral Negotiation League , 2018 .

[2]  Catholijn M. Jonker,et al.  The Fifth Automated Negotiating Agents Competition (ANAC 2014) , 2016, ANAC@AAMAS.

[3]  Luís Paulo Reis,et al.  DipBlue: A Diplomacy Agent with Strategic and Trust Reasoning , 2015, ICAART.

[4]  Carles Sierra,et al.  D-Brane: a diplomacy playing agent for automated negotiations research , 2017, Applied Intelligence.

[5]  Koen V. Hindriks,et al.  The first automated negotiating agents competition (ANAC 2010) , 2016 .

[6]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[7]  Carles Sierra,et al.  $$\hbox {NB}^{3}$$NB3: a multilateral negotiation algorithm for large, non-linear agreement spaces with limited time , 2015, Autonomous Agents and Multi-Agent Systems.

[8]  Henrique Lopes Cardoso,et al.  Towards General Cooperative Game Playing , 2018, Trans. Comput. Collect. Intell..

[9]  Dongmo Zhang,et al.  Automated Negotiations for General Game Playing , 2017, AAMAS.

[10]  Sarit Kraus,et al.  The First Automated Negotiating Agents Competition (ANAC 2010) , 2012, New Trends in Agent-Based Complex Automated Negotiations.

[11]  Catholijn M. Jonker,et al.  Results of the First Annual Human-Agent League of the Automated Negotiating Agents Competition , 2018, IVA.

[12]  Carles Sierra,et al.  DipGame: A challenging negotiation testbed , 2011, Eng. Appl. Artif. Intell..

[13]  Koen V. Hindriks,et al.  The Automated Negotiating Agents Competition, 2010-2015 , 2015, AI Mag..

[14]  Catholijn M. Jonker,et al.  ANAC 2018: Repeated Multilateral Negotiation League , 2018, JSAI.

[15]  Catholijn M. Jonker,et al.  A Baseline for Nonlinear Bilateral Negotiations: The full results of the agents competing in ANAC 2014 , 2016 .

[16]  Catholijn M. Jonker,et al.  A Baseline for Non-Linear Bilateral Negotiations The full results of the agents competing in ANAC 2014 , 2016 .