The game is a prototype of the social contract. [25] For more on the existential risks of Superintelligence, see Bostrom (2014) at Chapters 6 and 8. The Stag Hunt game, derived from Rousseaus story, describes the following scenario: a group of two or more people can cooperate to hunt down the more rewarding stag or go their separate ways and hunt less rewarding hares. Human security is an emerging paradigm for understanding global vulnerabilities whose proponents challenge the traditional notion of national security by arguing that the proper referent for security should be the individual rather than the state. No payoffs (that satisfy the above conditions including risk dominance) can generate a mixed strategy equilibrium where Stag is played with a probability higher than one half. Interestingly enough, the Stag Hunt theory can be used to describe social contracts within society, with the contract being the one to hunt the stag or achieve mutual benefit. [25] In a particularly telling quote, Stephen Hawking, Stuart Russell, Max Tegmark, and Frank Wilczek foreshadow this stark risk: One can imagine such technology outsmarting financial markets, out-inventing human researchers, out-manipulating human leaders, and developing weapons we cannot even understand. [28] Armstrong et al., Racing to the precipice: a model of artificial intelligence development.. In so doing, they have maintained a kind of limited access order, drawing material and political benefits from cooperating with one another, most recently as part of the current National Unity Government. If both choose to row they can successfully move the boat. If they both work to drain it they will be successful, but if either fails to do his part the meadow will not be drained. The coincident timing of high-profile talks with a leaked report that President Trump seeks to reduce troop levels by half has already triggered a political frenzy in Kabul. So it seems that the moral of the story is that we are selfish human beings with little patience or trust in others, even if that cooperation meant mutual benefit. endstream endobj 76 0 obj <>stream In short, the theory suggests that the variables that affect the payoff structure of cooperating or defecting from an AI Coordination Regime determine which model of coordination we see arise between the two actors (modeled after normal-form game setups). This article is about the game theory problem about stag hunting. (5OP,&|#5Y9/yU'4x r+g\t97ASNgQ+Oh iCcKzCx7<=nZefYt|.OPX:'.&|=_Ml_I{]+Mr`h+9UeovX.C; =a #/ q_/=02Q0U>#|Lod. 9i <> If, by contrast, the prospect of a return to anarchy looms, trust erodes and short-sighted self-interest wins the day. Solving this problem requires more understanding of its dynamics and strategic implications before hacking at it with policy solutions. At key moments, the cooperation among Afghan politicians has been maintained with a persuasive nudge from U.S. diplomats. On the face of it, it seems that the players can then 'agree' to play (c,c); though the agreement is not enforceable, it removes each player's doubt about the other one playing c". 7into the two-person Stag Hunt: This is an exact version of the8 informal arguments of Hume and Hobbes. So far, the readings discussed have commented on the unique qualities of technological or qualitative arms races. In these abstractions, we assume two utility-maximizing actors with perfect information about each others preferences and behaviors. This table contains an ordinal representation of a payoff matrix for a Chicken game. These strategies are not meant to be exhaustive by any means, but hopefully show how the outlined theory might provide practical use and motivate further research and analysis. This situation is often seen as a useful analogy for many kinds of social cooperation, such as international agreements on climate change.[1]. For example, if the two international actors cooperate with one another, we can expect some reduction in individual payoffs if both sides agree to distribute benefits amongst each other. Huntington[37] makes a distinction between qualitative arms races (where technological developments radically transform the nature of a countrys military capabilities) and quantitative arms races (where competition is driven by the sheer size of an actors arsenal). In this section, I survey the relevant background of AI development and coordination by summarizing the literature on the expected benefits and harms from developing AI and what actors are relevant in an international safety context. Most events in IR are not mutually beneficial, like in the Battle of the Sexes. Scholars of civil war have argued, for example, that peacekeepers can preserve lasting cease-fires by enabling warring parties to cooperate with the knowledge that their security will be guaranteed by a third party. Instead, each hunter should separately choose the more ambitious and far more rewarding goal of getting the stag, thereby giving up some autonomy in exchange for the other hunter's cooperation and added might. Other names for it or its variants include "assurance game", "coordination game", and "trust dilemma". Schelling and Halperin[44] offer a broad definition of arms control as all forms of military cooperation between potential enemies in the interest of reducing the likelihood of war, its scope and violence if it occurs, and the political and economic costs of being prepared for it.. For example, suppose we have a prisoner's dilemma as pictured in Figure 3. Additionally, both actors perceive the potential returns to developing AI to be greater than the potential harms. This may not amount to a recipe for good governance, but it has meant the preservation of a credible bulwark against state collapse. We see this in the media as prominent news sources with greater frequency highlight new developments and social impacts of AI with some experts heralding it as the new electricity.[10] In the business realm, investments in AI companies are soaring. Some have accused rivals of being Taliban sympathizers while others have condemned their counterparts for being against peace. These are a few basic examples of modeling IR problems with game theory. Nations are able to communicate with each other freely, something that is forbidden in the traditional PD game. Not wanting to miss out on the high geopolitical drama, Moscow invited Afghanistans former president, Hamid Karzai, and a cohort of powerful elitesamong them rivals of the current presidentto sit down with a Taliban delegation last week. PRICE CODE 17. This section defines suggested payoffs variables that impact the theory and simulate the theory for each representative model based on a series of hypothetical scenarios. 0000016501 00000 n The hedge is shared so both parties are responsible for maintaining it. Posted June 3, 2008 By Presh Talwalkar. Additionally, the feedback, discussion, resource recommendations, and inspiring work of friends, colleagues, and mentors in several time zones especially Amy Fan, Carrick Flynn, Will Hunt, Jade Leung, Matthijs Maas, Peter McIntyre, Professor Nuno Monteiro, Gabe Rissman, Thomas Weng, Baobao Zhang, and Remco Zwetsloot were vital to this paper and are profoundly appreciated. genocide, crimes against humanity, war crimes, and ethnic cleansing. This allows for coordination, and enables players to move from the strategy with the lowest combined payoff (both cheat) to the strategy with the highest combined payoff (both cooperate). [46] Charles Glaser, Realists as Optimists: Cooperation as Self-Help, International Security 19, 3(1994): 50-90. Nonetheless many would call this game a stag hunt. In international relations, examples of Chicken have included the Cuban Missile Crisis and the concept of Mutually Assured Destruction in nuclear arms development. One final strategy that a safety-maximizing actor can employ in order to maximize chances for cooperation is to change the type of game that exists by using strategies or policies to affect the payoff variables in play. The first technology revolution caused World War I. If a hunter leaps out and kills the hare, he will eat, but the trap laid for the stag will be wasted and the other hunters will starve. Cultural Identity - crucial fear of social systems. [39] D. S. Sorenson, Modeling the Nuclear Arms Race: A Search for Stability, Journal of Peace Science 4 (1980): 16985. The response from Kabul involved a predictable combination of derision and alarm, for fear that bargaining will commence on terms beyond the current administrations control. Before getting to the theory, I will briefly examine the literature on military technology/arms racing and cooperation. We can see through studying the Stag Hunt game theory that, even though we are selfish, we still are ironically aiming to for mutual benefit, and thus we tend to follow a such a social contract. Examples of the stag hunt [ edit] The original stag hunt dilemma is as follows: a group of hunters have tracked a large stag, and found it to follow a certain path. [56] look at three different types of strategies governments can take to reduce the level of arms competition with a rival: (1) a unilateral strategy where an actors individual actions impact race dynamics (for example, by focusing on shifting to defensive weapons[57]), (2) a tacit bargaining strategy that ties defensive expenditures to those of a rival, and (3) a negotiation strategy composed of formal arms talks. 0000018184 00000 n Those who play it safe will choose Several animal behaviors have been described as stag hunts. The hunters hide and wait along a path. [47] look at different policy responses to arms race de-escalation and find that the model or game that underlies an arms race can affect the success of policies or strategies to mitigate or end the race. Another proposed principle of rationality ("maximin") suggests that I ought to consider the worst payoff I could obtain under any course of action, and choose that action that maximizes . The familiar Prisoners Dilemma is a model that involves two actors who must decide whether to cooperate in an agreement or not. Similar strategic analyses can be done on variables and variable relationships outlined in this model. I thank my advisor, Professor Allan Dafoe, for his time, support, and introduction to this papers subject matter in his Global Politics of AI seminar. <<3B74F05AAAB3B2110A0010B6ACF6FC7F>]/Prev 397494>> In international relations, countries are the participants in the stag hunt. [53] A full list of the variables outlined in this theory can be found in Appendix A. Author James Cambias describes a solution to the game as the basis for an extraterrestrial civilization in his 2014 science fiction book A Darkling Sea. Formally, a stag hunt is a game with two pure strategy Nash equilibriaone that is risk dominant and another that is payoff dominant. Additionally, the defector can expect to receive the additional expected benefit of defecting and covertly pursuing AI development outside of the Coordination Regime. a [14] IBM, Deep Blue, Icons of Progress, http://www-03.ibm.com/ibm/history/ibm100/us/en/icons/deepblue/. I will apply them to IR and give an example for each. Downs et al. From that moment on, the tenuous bonds keeping together the larger band of weary, untrusting hunters will break and the stag will be lost. Together, the likelihood of winning and the likelihood of lagging = 1. Advanced AI technologies have the potential to provide transformative social and economic benefits like preventing deaths in auto collisions,[17] drastically improving healthcare,[18] reducing poverty through economic bounty,[19] and potentially even finding solutions to some of our most menacing problems like climate change.[20].