Resource balancing within complex transportation networks is one of the most important problems in real logistics domain. Traditional solutions on these problems leverage combinatorial optimization with demand and supply forecasting. However, the high complexity of transportation routes, severe uncertainty of future demand and supply, together with non-convex business constraints make it extremely challenging in the traditional resource management field. In this paper, we propose a novel sophisticated multi-agent reinforcement learning approach to address these challenges. In particular, inspired by the externalities especially the interactions among resource agents, we introduce an innovative cooperative mechanism for state and reward design resulting in more effective and efficient transportation. Extensive experiments on a simulated ocean transportation service demonstrate that our new approach can stimulate cooperation among agents and lead to much better performance. Compared with traditional solutions based on combinatorial optimization, our approach can give rise to a significant improvement in terms of both performance and stability.

The emergence of complex life on Earth is often attributed to the arms race that ensued from a huge number of organisms all competing for finite resources. We present an artificial intelligence research environment, inspired by the human game genre of MMORPGs (Massively Multiplayer Online Role-Playing Games, a.k.a. MMOs), that aims to simulate this setting in microcosm. As with MMORPGs and the real world alike, our environment is persistent and supports a large and variable number of agents. Our environment is well suited to the study of large-scale multiagent interaction: it requires that agents learn robust combat and navigation policies in the presence of large populations attempting to do the same. Baseline experiments reveal that population size magnifies and incentivizes the development of skillful behaviors and results in agents that outcompete agents trained in smaller populations. We further show that the policies of agents with unshared weights naturally diverge to fill different niches in order to avoid competition.

Having notched impressive victories over human professionals in Go, Atari Games, and most recently StarCraft 2 -- Google's DeepMind team has now turned its formidable research efforts to soccer. In a paper released last week, the UK AI company demonstrates a novel machine learning method that trains a team of AI agents to play a simulated version of "the beautiful game." Gaming, AI and soccer fans hailed DeepMind's latest innovation on social media, with comments like "You should partner with EA Sports for a FIFA environment!" Machine learning, and particularly deep reinforcement learning, has in recent years achieved remarkable success across a wide range of competitive games. Collaborative-multi-agent games however remained a relatively difficult research domain.

Collective intelligence is manifested when multiple agents coherently work in observation, interaction, decision-making and action. In this paper, we define and quantify the intelligence level of heterogeneous agents group with the improved Anytime Universal Intelligence Test(AUIT), based on an extension of the existing evaluation of homogeneous agents group. The relationship of intelligence level with agents composition, group size, spatial complexity and testing time is analyzed. The intelligence level of heterogeneous agents groups is compared with the homogeneous ones to analyze the effects of heterogeneity on collective intelligence. Our work will help to understand the essence of collective intelligence more deeply and reveal the effect of various key factors on group intelligence level.

In multi-agent path finding (MAPF), it is usually assumed that planning is performed centrally and that the destinations of the agents are common knowledge. We will drop both assumptions and analyze under which conditions it can be guaranteed that the agents reach their respective destinations using implicitly coordinated plans without communication. Furthermore, we will analyze what the computational costs associated with such a coordination regime are. As it turns out, guarantees can be given assuming that the agents are of a certain type. However, the implied computational costs are quite severe. In the distributed setting, we either have to solve a sequence of NP-complete problems or have to tolerate exponentially longer executions. In the setting with destination uncertainty, bounded plan existence becomes PSPACE-complete. This clearly demonstrates the value of communicating about plans before execution starts.

Modeling social interactions based on individual behavior has always been an area of interest, but prior literature generally presumes rational behavior. Thus, such models may miss out on capturing the effects of biases humans are susceptible to. This work presents a method to model egocentric bias, the real-life tendency to emphasize one's own opinion heavily when presented with multiple opinions. We use a symmetric distribution centered at an agent's own opinion, as opposed to the Bounded Confidence (BC) model used in prior work. We consider a game of iterated interactions where an agent cooperates based on its opinion about an opponent. Our model also includes the concept of domain-based self-doubt, which varies as the interaction succeeds or not. An increase in doubt makes an agent reduce its egocentricity in subsequent interactions, thus enabling the agent to learn reactively. The agent system is modeled with factions not having a single leader, to overcome some of the issues associated with leader-follower factions. We find that agents belonging to factions perform better than individual agents. We observe that an intermediate level of egocentricity helps the agent perform at its best, which concurs with conventional wisdom that neither overconfidence nor low self-esteem brings benefits.

A novel model developed by MIT and Microsoft researchers identifies instances in which autonomous systems have "learned" from training examples that don't match what's actually happening in the real world. Engineers could use this model to improve the safety of artificial intelligence systems, such as driverless vehicles and autonomous robots. The AI systems powering driverless cars, for example, are trained extensively in virtual simulations to prepare the vehicle for nearly every event on the road. But sometimes the car makes an unexpected error in the real world because an event occurs that should, but doesn't, alter the car's behavior. Consider a driverless car that wasn't trained, and more importantly doesn't have the sensors necessary, to differentiate between distinctly different scenarios, such as large, white cars and ambulances with red, flashing lights on the road.

In scenarios where a robot generates and executes a plan, there may be instances where this generated plan is less costly for the robot to execute but incomprehensible to the human. When the human acts as a supervisor and is held accountable for the robot's plan, the human may be at a higher risk if the incomprehensible behavior is deemed to be unsafe. In such cases, the robot, who may be unaware of the human's exact expectations, may choose to do (1) the most constrained plan (i.e. one preferred by all possible supervisors) incurring the added cost of executing highly sub-optimal behavior when the human is observing it and (2) deviate to a more optimal plan when the human looks away. These problems amplify in situations where the robot has to fulfill multiple goals and cater to the needs of different human supervisors. In such settings, the robot, being a rational agent, should take any chance it gets to deviate to a lower cost plan. On the other hand, continuous monitoring of the robot's behavior is often difficult for the human because it costs them valuable resources (eg. time, effort, cognitive overload etc.). To optimize the cost for constant monitoring while ensuring the robots follow the {\em safe} behavior, we model this problem in the game-theoretic framework of trust where the human is the agent that trusts the robot. We show that the notion of human's trust, which is well-defined when there is a pure strategy equilibrium, is inversely proportional to the probability it assigns for observing the robot's behavior. We then show that with high probability, our game lacks a pure strategy Nash equilibrium, forcing us to define a notion of trust boundary over mixed strategies of the human in order to guarantee safe behavior by the robot.

In recent years, there has been a great deal of coverage about the dearth of PhD qualified AI data-scientists and the level of salaries qualified candidates can gain. One such piece can be found here: NYTimes article. Then you have universities complaining how their PhD qualified AI scientists are being poached by the industry thus demonstrating the demand for PhD qualified AI scientists: Guardian Article. Also, you have many universities opening numerous funded AI PhD positions such as this university: Leeds University Isn't it then obvious, a PhD in AI technology should be on all data scientists to do list. Well, as one who contemplated briefly to do a second PhD (focusing on swarm intelligence and multi-agent system in Healthcare) and who spent some time researching the necessity of completing a PhD to be across AI, I found it detrimental to undertake a PhD focusing on a specific AI algorithmic approach. This article is not meant to signal an obituary for PhD's focusing AI, but a cautionary note for someone contemplating a PhD focusing on a specific AI technique.

Methods for learning and planning in sequential decision problems often assume the learner is aware of all possible states and actions in advance. This assumption is sometimes untenable. In this paper, we give a method to learn factored markov decision problems from both domain exploration and expert assistance, which guarantees convergence to near-optimal behaviour, even when the agent begins unaware of factors critical to success. Our experiments show our agent learns optimal behaviour on small and large problems, and that conserving information on discovering new possibilities results in faster convergence.