Newest Papers
Incorrigibility in the CIRL Framework
Ryan Carey
arXiv·2017
A value learning system has incentives to follow shutdown instructions, assuming the shutdown instruction provides information (in the technical sense) about which actions lead to valuable outcomes. However, this assumption is not robust to model mis-specification (e.g., in the case of programmer errors). We demonstrate this by presenting some Supervised POMDP scenarios in which errors in the parameterized reward function remove the incentive to follow shutdown commands. These difficulties parallel those discussed by Soares et al. (2015) in their paper on corrigibility. We argue that it is important to consider systems that follow shutdown commands under some weaker set of assumptions (e.g., that one small verified module is correctly implemented; as opposed to an entire prior probability distribution and/or parameterized reward function). We discuss some difficulties with simple ways to attempt to attain these sorts of guarantees in a value learning framework.
No ratings yet
View paper →Evolution of flexibility and rigidity in retaliatory punishment
Adam Morris, James MacGlashan, Michael L. Littman, Fiery Cushman
Proceedings of the National Academy of Sciences·2017·13 citations
<jats:p>Natural selection designs some social behaviors to depend on flexible learning processes, whereas others are relatively rigid or reflexive. What determines the balance between these two approaches? We offer a detailed case study in the context of a two-player game with antisocial behavior and retaliatory punishment. We show that each player in this game—a “thief” and a “victim”—must balance two competing strategic interests. Flexibility is valuable because it allows adaptive differentiation in the face of diverse opponents. However, it is also risky because, in competitive games, it can produce systematically suboptimal behaviors. Using a combination of evolutionary analysis, reinforcement learning simulations, and behavioral experimentation, we show that the resolution to this tension—and the adaptation of social behavior in this game—hinges on the game’s learning dynamics. Our findings clarify punishment’s adaptive basis, offer a case study of the evolution of social preferences, and highlight an important connection between natural selection and learning in the resolution of social conflicts.</jats:p>
No ratings yet
View paper →Now is the Time for a Postracial Medicine: Biomedical Research, the National Institutes of Health, and the Perpetuation of Scientific Racism
Javier Perez-Rodriguez, Alejandro de la Fuente
The American Journal of Bioethics·2017·37 citations
No abstract available
★ 3.0 (1)
View paper →THE CHALLENGES OF THE ANTHROPOCENE: FROM INTERNATIONAL ENVIRONMENTAL POLITICS TO GLOBAL GOVERNANCE
MATÍAS FRANCHINI, EDUARDO VIOLA, ANA FLÁVIA BARROS-PLATIAU
Ambiente & Sociedade·2017·22 citations
This article proposes a reflection on the challenges of global environmental policy in the Anthropocene. Firstly, the inconsistency between the institutions of international environmental policy and the progressive degradation of the planetary boundaries is highlighted. Secondly, it is stated that, since the transition to Anthropocene requires the conscious construction of a new space of safe operation for humanity, it is necessary to radically modify the institutional structure of cooperation, based on international regimes: the transition from environmental politics to global governance. The fundamental milestone of this path is the overcoming of the international system of conservative hegemony, that is, the abandonment of the sovereignist tendencies - egotistical and short-term - on the part of its actors, particularly the great powers. Finally, a series of premises for the governance of the Anthropocene is proposed from the point of view of International Relations, with the post-sovereign transition as the main pillar.
No ratings yet
View paper →