Dubbed ADEPT, the system is able to, like a human being, understand some laws of physics intuitively. It can look at an object in a video, predict how it should act based on what it knows of the laws of physics and then register surprise if what it was looking at subsequently vanishes or teleports. The team behind ADEPT say their model will allow other researchers to create smarter AIs in the future, as well give us a better understanding of how infants understand the world around them. "By the time infants are three months old, they have some notion that objects don't wink in and out of existence, and can't move through each other or teleport," said Kevin A. Smith, one of the researchers that created ADEPT. "We wanted to capture and formalize that knowledge to build infant cognition into artificial-intelligence agents. We're now getting near human-like in the way models can pick apart basic implausible or plausible scenes."

Department of Electrical, Electronic and Information Engineering Alma Mater Studiorum - Universit a di Bologna Bologna, Italy Abstract In this paper, we introduce the concept of collective learning (CL) which exploits the notion of collective intelligence in the field of distributed semi-supervised learning. The proposed framework draws inspiration from the learning behavior of human beings, who alternate phases involving collaboration, confrontation and exchange of views with other consisting of studying and learning on their own. On this regard, CL comprises two main phases: a self-training phase in which learning is performed on local private (labeled) data only and a collective training phase in which proxy-labels are assigned to shared (unlabeled) data by means of a consensus-based algorithm. In the considered framework, heterogeneous systems can be connected over the same network, each with different computational capabilities and resources and everyone in the network may take advantage of the cooperation and will eventually reach higher performance with respect to those it can reach on its own. An extensive experimental campaign on an image classification problem emphasizes the properties of CL by analyzing the performance achieved by the cooperating agents. 1 Introduction The notion of collective intelligence has been firstly introduced in [Engelbart, 1962] and widespread in the sociological field by Pierre L evy in [L evy and Bononno, 1997]. By borrowing the words of L evy, collective intelligence " is a form of universally distributed intelligence, constantly enhanced, coordinated in real time, and resulting in the effective mobilization of skills ". Moreover, " the basis and goal of collective intelligence is mutual recognition and enrichment of individuals rather than the cult of fetishized or hypostatized communities ". In this paper, we aim to exploit some concepts borrowed from the notion of collective intelligence in a distributed machine learning scenario. In fact, by cooperating with each other, machines may exhibit performance higher than those they can obtain by learning on their own. We call this framework collective learning (CL) . Distributed systems 1 have received a steadily growing attention in the last years and1 When talking about distributed systems, the word distributed can be used with different meanings.

We seek to align agent behavior with a user's objectives in a reinforcement learning setting with unknown dynamics, an unknown reward function, and unknown unsafe states. The user knows the rewards and unsafe states, but querying the user is expensive. To address this challenge, we propose an algorithm that safely and interactively learns a model of the user's reward function. We start with a generative model of initial states and a forward dynamics model trained on off-policy data. Our method uses these models to synthesize hypothetical behaviors, asks the user to label the behaviors with rewards, and trains a neural network to predict the rewards. The key idea is to actively synthesize the hypothetical behaviors from scratch by maximizing tractable proxies for the value of information, without interacting with the environment. We call this method reward query synthesis via trajectory optimization (ReQueST). We evaluate ReQueST with simulated users on a state-based 2D navigation task and the image-based Car Racing video game. The results show that ReQueST significantly outperforms prior methods in learning reward models that transfer to new environments with different initial state distributions. Moreover, ReQueST safely trains the reward model to detect unsafe states, and corrects reward hacking before deploying the agent.

For power grid operations, a large body of research focuses on using generation redispatching, load shedding or demand side management flexibilities. However, a less costly and potentially more flexible option would be grid topology reconfiguration, as already partially exploited by Coreso (European RSC) and RTE (French TSO) operations. Beyond previous work on branch switching, bus reconfigurations are a broader class of action and could provide some substantial benefits to route electricity and optimize the grid capacity to keep it within safety margins. Because of its non-linear and combinatorial nature, no existing optimal power flow solver can yet tackle this problem. We here propose a new framework to learn topology controllers through imitation and reinforcement learning. We present the design and the results of the first "Learning to Run a Power Network" challenge released with this framework. We finally develop a method providing performance upper-bounds (oracle), which highlights remaining unsolved challenges and suggests future directions of improvement.

Recently there has been an increase in the studies on time - series data mining specifically time - series clustering due to the vast existe nce of time - series in various domains. The large volume of data in the form of time - series make s it necessary to employ various techniques such as clustering to understand the data and to extract information and hidden patterns. In the field of clustering specifically, time - series clustering, the most important aspects are the similarity measure used and the algorithm employed to conduct the clustering. In this paper, a new similarity measure for time - series clustering is developed based on a combination of a simple representation of time - series, slope of each segment of time - series, Euclidean distance and the so - called dynamic time warping. It is proved in this paper that the proposed distance measure is metric and thus indexing can be applied. For the task of clustering, the Particle Swarm Optimization algorithm is employed. The proposed similarity measure is compared to three existing measures in terms of various criteria used for the evaluation of clustering algorithms. The results indicate that the propo sed similarity measure outperforms the rest in almost every dataset used in this paper.

Quality Diversity (QD) algorithms like Novelty Search with Local Competition (NSLC) and MAP-Elites are a new class of population-based stochastic algorithms designed to generate a diverse collection of quality solutions. Meanwhile, variants of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) are among the best-performing derivative-free optimizers in single-objective continuous domains. This paper proposes a new QD algorithm called Covariance Matrix Adaptation MAP-Elites (CMA-ME). Our new algorithm combines the dynamic self-adaptation techniques of CMA-ES with archiving and mapping techniques for maintaining diversity in QD. Results from experiments with standard continuous optimization benchmarks show that CMA-ME finds better-quality solutions than MAP-Elites; similarly, results on the strategic game Hearthstone show that CMA-ME finds both a higher overall quality and broader diversity of strategies than both CMA-ES and MAP-Elites. Overall, CMA-ME more than doubles the performance of MAP-Elites using standard QD performance metrics. These results suggest that QD algorithms augmented by operators from state-of-the-art optimization algorithms can yield high-performing methods for simultaneously exploring and optimizing continuous search spaces, with significant applications to design, testing, and reinforcement learning among other domains. Code is available for both the continuous optimization benchmark (https://github.com/tehqin/QualDivBenchmark) and Hearthstone (https://github.com/tehqin/EvoStone) domains.

Function approximation is a powerful approach for structuring large decision problems that has facilitated great achievements in the areas of reinforcement learning and game playing. Regression counterfactual regret minimization (RCFR) is a flexible and simple algorithm for approximately solving imperfect information games with policies parameterized by a normalized rectified linear unit (ReLU). In contrast, the more conventional softmax parameterization is standard in the field of reinforcement learning and has a regret bound with a better dependence on the number of actions in the tabular case. We derive approximation error-aware regret bounds for $(\Phi, f)$-regret matching, which applies to a general class of link functions and regret objectives. These bounds recover a tighter bound for RCFR and provides a theoretical justification for RCFR implementations with alternative policy parameterizations ($f$-RCFR), including softmax. We provide exploitability bounds for $f$-RCFR with the polynomial and exponential link functions in zero-sum imperfect information games, and examine empirically how the link function interacts with the severity of the approximation to determine exploitability performance in practice. Although a ReLU parameterized policy is typically the best choice, a softmax parameterization can perform as well or better in settings that require aggressive approximation.

We study reinforcement learning (RL) in a setting with a network of agents whose states and actions interact in a local manner where the objective is to find localized policies such that the (discounted) global reward is maximized. A fundamental challenge in this setting is that the state-action space size scales exponentially in the number of agents, rendering the problem intractable for large networks. In this paper, we propose a Scalable Actor-Critic (SAC) framework that exploits the network structure and finds a localized policy that is a $O(\rho^\kappa)$-approximation of a stationary point of the objective for some $\rho\in(0,1)$, with complexity that scales with the local state-action space size of the largest $\kappa$-hop neighborhood of the network.

-- In this paper, we propose SwarmNet - a neural network architecture that can learn to predict and imitate the behavior of an observed swarm of agents in a centralized manner . T ested on artificially generated swarm motion data, the network achieves high levels of prediction accuracy and imitation authenticity. We compare our model to previous approaches for modelling interaction systems and show how modifying components of other models gradually approaches the performance of ours. Finally, we also discuss an extension of SwarmNet that can deal with nondeterministic, noisy, and uncertain environments, as often found in robotics applications. Multi-Robot Systems (MRS) [1] describe groups of robotic agents that collectively perform complex tasks in a distributed and parallel manner through repeated interactions among each other and the environment. Such systems have attracted considerable attention in recent years with remarkable successes in a number of application domains, including defense, agriculture, logistics, disaster management, and entertainment. In particular, today's fast-paced online economy is largely fuelled by tens of thousands of warehouse robots that transport millions of items across fulfillment centers all over the world. Despite this progress, programming groups of robots to perform a joint task is still considered a complex, time-consuming, and extremely challenging endeavour. One prominent formalism for the specification of MRS is based on the identification of cost functions [2] governing the group behavior. However, this approach is not intuitive and requires a deep understanding of complex theoretical concepts across a number of mathematical fields, e.g., graph theory, manifold theory, nonlinear optimization, etc. In addition, the real-world ramifications of even small changes in a given cost function are extremely difficult to foresee.

Recent superhuman results in games have largely been achieved in a variety of zero-sum settings, such as Go and Poker, in which agents need to compete against others. However, just like humans, real-world AI systems have to coordinate and communicate with other agents in cooperative partially observable environments as well. These settings commonly require participants to both interpret the actions of others and to act in a way that is informative when being interpreted. Those abilities are typically summarized as theory of mind and are seen as crucial for social interactions. In this paper we propose two different search techniques that can be applied to improve an arbitrary agreed-upon policy in a cooperative partially observable game. The first one, single-agent search, effectively converts the problem into a single agent setting by making all but one of the agents play according to the agreed-upon policy. In contrast, in multi-agent search all agents carry out the same common-knowledge search procedure whenever doing so is computationally feasible, and fall back to playing according to the agreed-upon policy otherwise. We prove that these search procedures are theoretically guaranteed to at least maintain the original performance of the agreed-upon policy (up to a bounded approximation error). In the benchmark challenge problem of Hanabi, our search technique greatly improves the performance of every agent we tested and when applied to a policy trained using RL achieves a new state-of-the-art score of 24.61 / 25 in the game, compared to a previous-best of 24.08 / 25. Introduction Real-world situations such as driving require humans to coordinate with others in a partially-observable environment with limited communication. In such environments, humans have a mental model of how other agents will behave in different situations (theory of mind). This model allows them to change their beliefs about the world based on why they think an agent acted as they did, as well as predict how their own actions will affect others' future behavior. Together, these capabilities allow humans to search for a good action to take while accounting for the behavior of others.