.png){kind=icon}
.png){kind=icon}
Return
Cooperating with machines
.png){kind=icon}
OA
AI
DOI：10.1038/s41467-017-02597-8.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Since Alan Turing envisioned artificial intelligence, technical progress has often been measured by the ability to defeat humans in zero-sum encounters (e.g., Chess, Poker, or Go). Less attention has been given to scenarios in which human-machine cooperation is beneficial but non-trivial, such as scenarios in which human and machine preferences are neither fully aligned nor fully in conflict. Cooperation does not require sheer computational power, but instead is facilitated by intuition, cultural norms, emotions, signals, and pre-evolved dis-positions. Here, we develop an algorithm that combines a state-of-the-art reinforcementlearning algorithm with mechanisms for signaling. We show that this algorithm can cooperate with people and other algorithms at levels that rival human cooperation in a variety of two-player repeated stochastic games. These results indicate that general human-machine cooperation is achievable using a non-trivial, but ultimately simple, set of algorithmic mechanisms.
Keywords:
ITERATED PRISONERS-DILEMMA
REPEATED GAMES
SOCIAL DILEMMAS
ROBOTS
COMMUNICATION
STRATEGIES
EVOLUTION
NETWORKS
POKER
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
15.7
Papers:
9.2W
Citations:
91.2W
View more organizations