But if the narrative of the present is one of "prediction machines," referencing the book of the same title by Ajay Agrawal, Joshua Gans, and Avi Goldfarb, the narrative of the future will belong to "decision machines." If the narrative of the present is one of managers who are valued for showing judgment in decision making -- don't tell me whether someone will do well on the job, or whether a new product will win in the marketplace, but tell me instead who I should hire, which products I should bet on -- then the narrative of the future will be one in which we are valued for our ability to judge and shape the decision-making capabilities of machines. Artificial intelligence (AI) is the pursuit of machines that are able to act purposefully to make decisions towards the pursuit of goals. Machines need to be able to predict to decide, but decision making requires much more. Decision making requires bringing together and reconciling multiple points of view.

This paper c onsider s the problem of dynamic task allocation, where tasks are unknowingly distributed over an environment. We aim to address the multi - robot exploration aspect of the problem, while solving the task - allocation aspect. To that end, we first propose a novel nature - inspired approach called "hunter and gatherer". W e consider each task comprised of two sequential su btasks: detection and completion, where each subtask can only be carried out by a certain type of agent. Thus, this approach employs two complementary teams of agents: one agile in detecting (hunters) and another dexterous in completing (gatherers) the tasks. Then, we propose a multi - robot exploration algorithm for hunters and a multi - robot task allocation algorithm for gatherer s, both in distributed manner and based on innovative notions of "certainty and uncertainty profit margins". Statistical analysis on simulation results confirm the efficacy of the proposed algorithms. Besides, it is statistically prove n that the proposed s olutions function fairly, i.e. for each type of agent, the overall workload is distributed equally. I. Introduction Multi - robot systems are expected to complete tasks that are unfeasible, laborious or inefficient for a single agent to accomplish [1] . Employing multi - robot systems entails addressing various problems on the subject of task allocation [2], exploration [3], coordination [4], learning [5], and heterogeneity [6] . Among all these problems, the problem of multi - robot task allocation (MRTA), assign ing a group of tasks to individual robots, is the most deep - seated problems of multi - robot systems, where its complexity increases considerably by a wide variety of factors. Regarding, a MRTA problem where tasks are unknowingly distributed over an environment needs to be addressed by solving the problem from both MRTA and multi - ro bot exploration perspectives. This problem can even get more complicated if each task is divided into two sequential subtasks and each subtask can only be carried out by a certain type of agent.

Consider a dynamic task allocation problem, where tasks are unknowingly distributed over an environment . This paper considers ea ch task comprised of two sequential subtasks: detection and completion, where e ach subtask can only be carried out by a certain type of agent . We address th is problem using a novel natur e - inspired approach called "hunter and gathere r" . Th e proposed method employs two complementary teams of agents: one agile in detecting (hunters) and another dexterous in completing (gathere r s) the tasks . To minimize the collective cost of task accomplishments in a distributed manner, a game - theor etic solution is introduced to couple agents from complementary teams . We utiliz e market - based negotiation models to develop incentive - based decision - making algorithms rely ing on innovative notions of " certainty and uncertainty profit margins " . The simulation results demonstrate that employing two complementary teams of hunters and gatherers can effectually improve the number of tasks completed by agents compared to conventional methods, while the collec tive cost of accomplishments is minimized . In addition, t he stability and efficacy of the proposed solutions are studied using Nash equilibrium analysis and statistical analysis respectively . It is also numerically show n that the proposed solution s function fairly, i.e. for each type of agent, the overall w orkload is distributed equally . Index Terms -- Distributed multiagent system, dynamic task allocation, game theory, negotiation. Multirobot systems are expected to undertake imperative roles in a wide variety of fields such as urban search and rescue (USAR) [1, 2], agricultural field operations [3], security patrols [4, 5], environmental monitoring [6], and industrial procedures [7] . Studies have shown that multi - robot systems have advantage over single - robot systems by offering more reliability, redundancy, and time efficiency when the nature of the tasks is inherently dist ributed [8] . Nonetheless, the problem of multi - robot task - allocation (MRTA) poses many critical challenges that has called for investigation in the past two decades [9 - 11] . In this regards, t he complexity of MRTA problems increases significantly in a dynamic environment, where the number and location of tasks are unknown for agents [12, 13] . Thus, robot s need to explore the environment to find tasks before accomplishing them.

Previous research into agent communication has shown that a pre-trained guide can speed up the learning process of an imitation learning agent. The guide achieves this by providing the agent with discrete messages in an emerged language about how to solve the task. We extend this one-directional communication by a one-bit communication channel from the learner back to the guide: It is able to ask the guide for help, and we limit the guidance by penalizing the learner for these requests. During training, the agent learns to control this gate based on its current observation. We find that the amount of requested guidance decreases over time and guidance is requested in situations of high uncertainty. We investigate the agent's performance in cases of open and closed gates and discuss potential motives for the observed gating behavior.

All living organisms struggle against the forces of nature to carve out niches where they can maintain homeostasis. We propose that such a search for order amidst chaos might offer a unifying principle for the emergence of useful behaviors in artificial agents. We formalize this idea into an unsupervised reinforcement learning method called surprise minimizing RL (SMiRL). SMiRL trains an agent with the objective of maximizing the probability of observed states under a model trained on previously seen states. The resulting agents can acquire proactive behaviors that seek out and maintain stable conditions, such as balancing and damage avoidance, that are closely tied to an environment's prevailing sources of entropy, such as wind, earthquakes, and other agents. We demonstrate that our surprise minimizing agents can successfully play Tetris, Doom, control a humanoid to avoid falls and navigate to escape enemy agents, without any task-specific reward supervision. We further show that SMiRL can be used together with a standard task reward to accelerate reward-driven learning.

We've built an AI bot that achieves state-of-the-art results in Hanabi, a collaborative card game that has been cited as a benchmark game for AI research because it features both cooperative gameplay and imperfect information. Our bot outperforms previous AI algorithms at Hanabi by using real-time search to fine-tune its decisions during gameplay. It's the first bot to exceed elite human performance in the game, as judged by experienced players who have evaluated it. Researchers have found it challenging to apply search beyond perfect-information games like chess and Go. Our success with Hanabi suggests search can improve more AI systems and eventually help build AI that learns to master complex cooperative tasks in real-world settings.

Countless tech platforms are setting out to help call centers automate conversations with their customers. But U.S-Indian startup and Y Combinator alum Observe.ai is bucking that trend by using AI to help coach human call center workers, rather than replace them. Today the company announced it has raised $26 million in a series A round of funding to further this mission. It then automatically transcribes each call and carries out sentiment analysis to determine customer satisfaction while drawing correlations between the words and actions of the support agent and the happiness of the customer. Top-performing agents can be used as benchmarks to determine what works, which can then help train new or under-performing support staff.

Memento broke many of the traditional paradigms in the film industry by structuring two parallel narratives, one chronologically going backwards and one going forward. The novel form narrative implemented in Memento forces the audience to constantly reevaluate their knowledge of the plot and they keep learning small details every few minutes of the film. It turns out that replaying a knowledge sequence backwards for small time intervals is an incredibly captivating method of learning. Intuitively, the Memento form of learning seems like perfect for AI agents. Last year, researchers from OpenAI leveraged that learning methodology to created AI agents that learned to play Montezuma's Revenge using a single demonstration.

Hanabi is a new game that combines cooperation between players with imperfect information.

Federated learning opens a number of research opportunities due to its high communication efficiency in distributed training problems within a star network. In this paper, we focus on improving the communication efficiency for fully decentralized federated learning over a graph, where the algorithm performs local updates for several iterations and then enables communications among the nodes. In such a way, the communication rounds of exchanging the common interest of parameters can be saved significantly without loss of optimality of the solutions. Multiple numerical simulations based on large, real-world electronic health record databases showcase the superiority of the decentralized federated learning compared with classic methods.