Confronting barriers to human-robot cooperation: balancing efficiency and risk in machine behavior.

Many technical and psychological challenges make it difficult to design machines that effectively cooperate with people. To better understand these challenges, we conducted a series of studies investigating human-human, robot-robot, and human-robot cooperation in a strategically rich resource-sharing scenario, which required players to balance efficiency, fairness, and risk. In these studies, both human-human and robot-robot dyads typically learned efficient and risky cooperative solutions when they could communicate. In the absence of communication, robot dyads still often learned the same efficient solution, but human dyads achieved a less efficient (less risky) form of cooperation. This difference in how people and machines treat risk appeared to discourage human-robot cooperation, as human-robot dyads frequently failed to cooperate without communication. These results indicate that machine behavior should better align with human behavior, promoting efficiency while simultaneously considering human tendencies toward risk and fairness.

Machine behaviour.

Machines powered by artificial intelligence increasingly mediate our social, cultural, economic and political interactions. Understanding the behaviour of artificial intelligence systems is essential to our ability to control their actions, reap their benefits and minimize their harms. Here we argue that this necessitates a broad scientific research agenda to study machine behaviour that incorporates and expands upon the discipline of computer science and includes insights from across the sciences. We first outline a set of questions that are fundamental to this emerging field and then explore the technical, legal and institutional constraints on the study of machine behaviour.

Cooperating with machines.

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 dispositions. Here, we develop an algorithm that combines a state-of-the-art reinforcement-learning 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.

rRNA mutations that inhibit transfer-messenger RNA activity on stalled ribosomes.

In eubacteria, stalled ribosomes are rescued by a conserved quality-control mechanism involving transfer-messenger RNA (tmRNA) and its protein partner, SmpB. Mimicking a tRNA, tmRNA enters stalled ribosomes, adds Ala to the nascent polypeptide, and serves as a template to encode a short peptide that tags the nascent protein for destruction. To further characterize the tagging process, we developed two genetic selections that link tmRNA activity to cell death. These negative selections can be used to identify inhibitors of tagging or to identify mutations in key residues essential for ribosome rescue. Little is known about which ribosomal elements are specifically required for tmRNA activity. Using these selections, we isolated rRNA mutations that block the rescue of ribosomes stalled at rare Arg codons or at the inefficient termination signal Pro-opal. We found that deletion of A1150 in the 16S rRNA blocked tagging regardless of the stalling sequence, suggesting that it inhibits tmRNA activity directly. The C889U mutation in 23S rRNA, however, lowered tagging levels at Pro-opal and rare Arg codons, but not at the 3' end of an mRNA lacking a stop codon. We concluded that the C889U mutation does not inhibit tmRNA activity per se but interferes with an upstream step intermediate between stalling and tagging. C889 is found in the A-site finger, where it interacts with the S13 protein in the small subunit (forming intersubunit bridge B1a).