Show simple item record

dc.contributor.authorLong, William Fu
dc.date.accessioned2020-08-28T09:31:49Z
dc.date.created2019-05
dc.date.issued2019-08-23
dc.date.submitted2019
dc.identifier.citationLong, William Fu. 2019. Escaping the State of Nature: A Hobbesian Approach to Cooperation in Multi-Agent Reinforcement Learning. Bachelor's thesis, Harvard College.
dc.identifier.urihttps://nrs.harvard.edu/URN-3:HUL.INSTREPOS:37364611*
dc.description.abstractCooperation is a phenomenon that has been widely studied across many different disciplines. In the field of computer science, the modularity and robustness of multi-agent systems offer significant practical advantages over individual machines. At the same time, agents using standard independent reinforcement learning algorithms often fail to achieve long-term, cooperative strategies in unstable environments when there are short-term incentives to defect. Political philosophy, on the other hand, studies the evolution of cooperation in humans who face similar incentives to act individualistically, but nevertheless succeed in forming societies. Thomas Hobbes in Leviathan provides the classic analysis of the transition from a pre-social State of Nature, where consistent defection results in a constant state of war, to stable political community through the institution of an absolute Sovereign. This thesis argues that Hobbes’s natural and moral philosophy are strikingly applicable to artificially intelligent agents and aims to show that his political solutions are experimentally successful in producing cooperation among modified Q-Learning agents. Cooperative play is achieved in a novel Sequential Social Dilemma called the Civilization Game, which models the State of Nature by introducing the Hobbesian mechanisms of (1) opponent learning awareness and (2) majoritarian voting, leading to (3) the establishment of a Sovereign.
dc.description.sponsorshipComputer Science
dc.description.sponsorshipComputer Science
dc.format.mimetypeapplication/pdf
dc.language.isoen
dash.licenseLAA
dc.titleEscaping the State of Nature: A Hobbesian Approach to Cooperation in Multi-Agent Reinforcement Learning
dc.typeThesis or Dissertation
dash.depositing.authorLong, William Fu
dc.date.available2020-08-28T09:31:49Z
thesis.degree.date2019
thesis.degree.grantorHarvard College
thesis.degree.grantorHarvard College
thesis.degree.levelUndergraduate
thesis.degree.levelUndergraduate
thesis.degree.nameAB
thesis.degree.nameAB
dc.type.materialtext
thesis.degree.departmentComputer Science
thesis.degree.departmentComputer Science
dash.identifier.vireo
dash.author.emailwlong0827@gmail.com


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record