Coordinating multiple interacting agents to achieve a common goal is a difficult task with huge applicability. This problem remains hard to solve, even when limiting interactions to be mediated via a static interaction-graph. We present a novel approximate solution method for multi-agent Markov decision problems on graphs, based on variational perturbation theory. We adopt the strategy of planning via inference, which has been explored in various prior works. We employ a non-trivial extension of a novel high-order variational method that allows for approximate inference in large networks and has been shown to surpass the accuracy of existing variational methods. To compare our method to two state-of-the-art methods for multi-agent planning on graphs, we apply the method different standard GMDP problems. We show that in cases, where the goal is encoded as a non-local cost function, our method performs well, while state-of-the-art methods approach the performance of random guess. In a final experiment, we demonstrate that our method brings significant improvement for synchronization tasks.

This article presents a novel algorithm for promoting cooperation between internal actors in a goal-conditioned hierarchical reinforcement learning (HRL) policy. Current techniques for HRL policy optimization treat the higher and lower level policies as separate entities which are trained to maximize different objective functions, rendering the HRL problem formulation more similar to a general sum game than a single-agent task. Within this setting, we hypothesize that improved cooperation between the internal agents of a hierarchy can simplify the credit assignment problem from the perspective of the high-level policies, thereby leading to significant improvements to training in situations where intricate sets of action primitives must be performed to yield improvements in performance. In order to promote cooperation within this setting, we propose the inclusion of a connected gradient term to the gradient computations of the higher level policies. Our method is demonstrated to achieve superior results to existing techniques in a set of difficult long time horizon tasks.

In recent years we have seen fast progress on a number of benchmark problems in AI, with modern methods achieving near or super human performance in Go, Poker and Dota. One common aspect of all of these challenges is that they are by design adversarial or, technically speaking, zero-sum. In contrast to these settings, success in the real world commonly requires humans to collaborate and communicate with others, in settings that are, at least partially, cooperative. In the last year, the card game Hanabi has been established as a new benchmark environment for AI to fill this gap. In particular, Hanabi is interesting to humans since it is entirely focused on theory of mind, i.e., the ability to effectively reason over the intentions, beliefs and point of view of other agents when observing their actions. Learning to be informative when observed by others is an interesting challenge for Reinforcement Learning (RL): Fundamentally, RL requires agents to explore in order to discover good policies. However, when done naively, this randomness will inherently make their actions less informative to others during training. We present a new deep multi-agent RL method, the Simplified Action Decoder (SAD), which resolves this contradiction exploiting the centralized training phase. During training SAD allows other agents to not only observe the (exploratory) action chosen, but agents instead also observe the greedy action of their team mates. By combining this simple intuition with best practices for multi-agent learning, SAD establishes a new SOTA for learning methods for 2-5 players on the self-play part of the Hanabi challenge. Our ablations show the contributions of SAD compared with the best practice components. All of our code and trained agents are available at https://github.com/facebookresearch/Hanabi_SAD.

Machine learning techniques are currently used extensively for automating various cybersecurity tasks. Most of these techniques utilize supervised learning algorithms that rely on training the algorithm to classify incoming data into different categories, using data encountered in the relevant domain. A critical vulnerability of these algorithms is that they are susceptible to adversarial attacks where a malicious entity called an adversary deliberately alters the training data to misguide the learning algorithm into making classification errors. Adversarial attacks could render the learning algorithm unsuitable to use and leave critical systems vulnerable to cybersecurity attacks. Our paper provides a detailed survey of the state-of-the-art techniques that are used to make a machine learning algorithm robust against adversarial attacks using the computational framework of game theory. We also discuss open problems and challenges and possible directions for further research that would make deep machine learning-based systems more robust and reliable for cybersecurity tasks.

Personal use of this material is permitted. Abstract -- Increasing interest in integrating advanced robotics within manufacturing has spurred a renewed concentration in developing real-time scheduling solutions to coordinate human-robot collaboration in this environment. Traditionally, the problem of scheduling agents to complete tasks with temporal and spatial constraints has been approached either with exact algorithms, which are computationally intractable for large-scale, dynamic coordination, or approximate methods that require domain experts to craft heuristics for each application. We seek to overcome the limitations of these conventional methods by developing a novel graph attention network formulation to automatically learn features of scheduling problems to allow their deployment. T o learn effective policies for combinatorial optimization problems via machine learning, we combine imitation learning on smaller problems with deep Q-learning on larger problems, in a nonparametric framework, to allow for fast, near-optimal scheduling of robot teams. We show that our network-based policy finds at least twice as many solutions over prior state-of-the-art methods in all testing scenarios. I. INTRODUCTION Advances in robotic technology are enabling the introduction of mobile robots into manufacturing environments alongside human workers. By removing the cage around traditional robot platforms and integrating dynamic, final assembly operations with human-robot teams, manufacturers can see improvements in reducing a factory's footprint and environmental costs, as well as increased productivity [1].

Many problems can be viewed as games, where one or more agents try to ensure that certain objectives hold no matter t he behavior from the environment and other agents. In recent years, a num ber of logical formalisms have been proposed for specifying games amo ng which the Game Description Language (GDL) was established as the o fficial language for General Game Playing. Although numbers are rec urring in games, the description of games with numerical features in G DL requires the enumeration from all possible numeric values and the rel ation among them. Thereby, in this paper, we introduce the Game Descript ion Logic with Integers (GDLZ) to describe games with numerical varia bles, numerical parameters, as well as to perform numerical compari sons. We compare our approach with GDL and show that when describing t he same game, GDLZ is more compact.

We consider a sparse multi-task regression framework for fitting a collection of related sparse models. Representing models as nodes in a graph with edges between related models, a framework that fuses lasso regressions with the total variation penalty is investigated. Under a form of restricted eigenvalue assumption, bounds on prediction and squared error are given that depend upon the sparsity of each model and the differences between related models. This assumption relates to the smallest eigenvalue restricted to the intersection of two cone sets of the covariance matrix constructed from each of the agents' covariances. We show that this assumption can be satisfied if the constructed covariance matrix satisfies a restricted isometry property. In the case of a grid topology high-probability bounds are given that match, up to log factors, the no-communication setting of fitting a lasso on each model, divided by the number of agents. A decentralised dual method that exploits a convex-concave formulation of the penalised problem is proposed to fit the models and its effectiveness demonstrated on simulations against the group lasso and variants.

Some researchers have speculated that capable reinforcement learning (RL) agents pursuing misspecified objectives are often incentivized to seek resources and power in pursuit of those objectives. An agent seeking power is incentivized to behave in undesirable ways, including rationally preventing deactivation and correction. Others have voiced skepticism: humans seem idiosyncratic in their urges to power, which need not be present in the agents we design. We formalize a notion of power within the context of finite deterministic Markov decision processes (MDPs). We prove that, with respect to a wide class of reward function distributions, optimal policies tend to seek power over the environment.

To achieve these common goals, agents in a MAS should be capable of interacting with other agents, not simply by exchanging data, but by engaging as in social activities, such as those people participate in their daily lives: cooperation, coordination, negotiation, and the like. In MASs, agents are assumed to be autonomous - capable of making independent decisions about to do in order to satisfy their design objectives, and thus they need mechanisms that allow them to synchronize and to coordinate their activities at run time [31]. Although one of the main issues in MASs is the agents' coordination structure, this is not hard-wired at design time, as MASs are typically in standard concurrent/distributed systems. One well-known strategy for coordination in MAS is the design of multi-agent coordinated plans [7][35][36][33][14] that include, not only usual agents' actions defined by their effectors, but also communication actions to achieve the necessary synchronization and coordination. To represent communication actions, some specific languages were created, e.g.

This paper attempts to design an intelligent simulation model for pedestrian crowd evacuation. For this purpose, the cellular automata (CA) was fully integrated with fuzzy logi c, the k th nearest neighbors ( K NN), and some statistical equations. In this model, each pedestrian was assigned a specific speed, according to his/her physical, biological and emotional features. The emergency behavior and evacuation efficiency of each pedestrian were evaluated by coupling his/her speed with various elements, such as environment, pedestrian distribution and familiarity with the exits. These elements all have great impacts on the ev acuation process. Several experiments were carried out to verify the performance of the model in different emergency scenarios. The results show that the proposed model can predict the evacuation time and emergency behavior in various types of building int eriors and pedestrian distributions. The research provides a good reference to the design of building evacuation systems.