We propose a federated methodology to learn low-dimensional representations from a dataset that is distributed among several clients. In particular, we move away from the commonly-used cross-entropy loss in federated learning, and seek to learn shared low-dimensional representations of the data in a decentralized manner via the principle of maximal coding rate reduction (MCR2). Our proposed method, which we refer to as FLOW, utilizes MCR2 as the objective of choice, hence resulting in representations that are both between-class discriminative and within-class compressible. We theoretically show that our distributed algorithm achieves a first-order stationary point. Moreover, we demonstrate, via numerical experiments, the utility of the learned low-dimensional representations.

Evolutionary algorithms (EAs) provide unique advantages for optimizing neural networks in complex search spaces. This paper introduces a new web platform, NeuroEvo (neuroevo.io), that allows users to interactively design and train neural network classifiers using evolutionary and particle swarm algorithms. The classification problem and training data are provided by the user and, upon completion of the training process, the best classifier is made available to download and implement in Python, Java, and JavaScript. NeuroEvo is a cloud-based application that leverages GPU parallelization to improve the speed with which the independent evolutionary steps, such as mutation, crossover, and fitness evaluation, are executed across the population. This paper outlines the training algorithms and opportunities for users to specify design decisions and hyperparameter settings. The algorithms described in this paper are also made available as a Python package, neuroevo (PyPI: https://pypi.org/project/neuroevo/).

Recent progress in state-only imitation learning extends the scope of applicability of imitation learning to real-world settings by relieving the need for observing expert actions. However, existing solutions only learn to extract a state-to-action mapping policy from the data, without considering how the expert plans to the target. This hinders the ability to leverage demonstrations and limits the flexibility of the policy. In this paper, we introduce Decoupled Policy Optimization (DePO), which explicitly decouples the policy as a high-level state planner and an inverse dynamics model. With embedded decoupled policy gradient and generative adversarial training, DePO enables knowledge transfer to different action spaces or state transition dynamics, and can generalize the planner to out-of-demonstration state regions. Our in-depth experimental analysis shows the effectiveness of DePO on learning a generalized target state planner while achieving the best imitation performance. We demonstrate the appealing usage of DePO for transferring across different tasks by pre-training, and the potential for co-training agents with various skills.

The main goal of this paper is to derive a decentralized algorithm which can efficiently learn the gradient of a black-box model, in a multi-agent context. In a black-box model it is assumed that a function f is unknown but can be accessed through queries to a zero-th order oracle [6]. Being able to compute the gradient can be used, for instance to design efficient distributed optimization algorithms to find the minimum of f. We assume that there is a finite number of processors/servers (called nodes or agents in the rest of the paper) which participate in the distributed computation of the gradient. We also assume that some agents can have Byzantine behaviors: that is, they will try to deviate from the suggested protocol. Such behaviors are well known in the literature of distributed algorithms (consensus and leader election algorithms, for instance) and have also recently been studied in the context of machine learning [7, 12, 11]. In such contexts, three major points need to be tackled: (1) The fact that unidentifiable Byzantines nodes are present in the system and that it is not possible to guarantee the safety of a given node; (2) the algorithms should be decentralized and each "good" node, should have a good estimation of the gradient (3) the algorithms should be efficient (in terms of speed of convergence and number of operations per iterations). Our solution is based on a generalization of the gradient estimator algorithm developed in [4], using two-timescale stochastic approximations and secure estimation [8]. We are also able to derive sufficient conditions to ensure that our algorithm will be able to be robust to Byzantine nodes.

In this paper, we formalise and implement an agent model for cooperation under imperfect information. It is based on Theory of Mind (the cognitive ability to understand the mental state of others) and abductive reasoning (the inference paradigm that computes explanations from observations). The combination of these two techniques allows agents to derive the motives behind the actions of their peers, and incorporate this knowledge into their own decision-making. We have implemented this model in a totally domain-independent fashion and successfully tested it for the cooperative card game Hanabi.

As robots become increasingly complex, they must explain their behaviors to gain trust and acceptance. However, it may be difficult through verbal explanation alone to fully convey information about past behavior, especially regarding objects no longer present due to robots' or humans' actions. Humans often try to physically mimic past movements to accompany verbal explanations. Inspired by this human-human interaction, we describe the technical implementation of a system for past behavior replay for robots in this tool paper. Specifically, we used Behavior Trees to encode and separate robot behaviors, and schemaless MongoDB to structurally store and query the underlying sensor data and joint control messages for future replay. Our approach generalizes to different types of replays, including both manipulation and navigation replay, and visual (i.e., augmented reality (AR)) and auditory replay. Additionally, we briefly summarize a user study to further provide empirical evidence of its effectiveness and efficiency. Sample code and instructions are available on GitHub at https://github.com/umhan35/robot-behavior-replay.

An integral part of seamless human-human communication is engagement, the process by which two or more participants establish, maintain, and end their perceived connection. Therefore, to develop successful human-centered human-machine interaction applications, automatic engagement inference is one of the tasks required to achieve engaging interactions between humans and machines, and to make machines attuned to their users, hence enhancing user satisfaction and technology acceptance. Several factors contribute to engagement state inference, which include the interaction context and interactants' behaviours and identity. Indeed, engagement is a multi-faceted and multi-modal construct that requires high accuracy in the analysis and interpretation of contextual, verbal and non-verbal cues. Thus, the development of an automated and intelligent system that accomplishes this task has been proven to be challenging so far. This paper presents a comprehensive survey on previous work in engagement inference for human-machine interaction, entailing interdisciplinary definition, engagement components and factors, publicly available datasets, ground truth assessment, and most commonly used features and methods, serving as a guide for the development of future human-machine interaction interfaces with reliable context-aware engagement inference capability. An in-depth review across embodied and disembodied interaction modes, and an emphasis on the interaction context of which engagement perception modules are integrated sets apart the presented survey from existing surveys.

Human decision making is well known to be imperfect and the ability to analyse such processes individually is crucial when attempting to aid or improve a decision-maker's ability to perform a task, e.g. to alert them to potential biases or oversights on their part. To do so, it is necessary to develop interpretable representations of how agents make decisions and how this process changes over time as the agent learns online in reaction to the accrued experience. To then understand the decision-making processes underlying a set of observed trajectories, we cast the policy inference problem as the inverse to this online learning problem. By interpreting actions within a potential outcomes framework, we introduce a meaningful mapping based on agents choosing an action they believe to have the greatest treatment effect. We introduce a practical algorithm for retrospectively estimating such perceived effects, alongside the process through which agents update them, using a novel architecture built upon an expressive family of deep state-space models. Through application to the analysis of UNOS organ donation acceptance decisions, we demonstrate that our approach can bring valuable insights into the factors that govern decision processes and how they change over time.

We present MUG, a novel interactive task for multimodal grounding where a user and an agent work collaboratively on an interface screen. Prior works modeled multimodal UI grounding in one round: the user gives a command and the agent responds to the command. Yet, in a realistic scenario, a user command can be ambiguous when the target action is inherently difficult to articulate in natural language. MUG allows multiple rounds of interactions such that upon seeing the agent responses, the user can give further commands for the agent to refine or even correct its actions. Such interaction is critical for improving grounding performances in real-world use cases. To investigate the problem, we create a new dataset that consists of 77,820 sequences of human user-agent interaction on mobile interfaces in which 20% involves multiple rounds of interactions. To establish our benchmark, we experiment with a range of modeling variants and evaluation strategies, including both offline and online evaluation-the online strategy consists of both human evaluation and automatic with simulators. Our experiments show that allowing iterative interaction significantly improves the absolute task completion by 18% over the entire test dataset and 31% over the challenging subset. Our results lay the foundation for further investigation of the problem.

Multi-agent pathfinding (MAPF) is an NP-hard problem. As such, dense maps may be very hard to solve optimally. In such scenarios, compilation-based approaches, via Boolean satisfiability (SAT) and answer set programming (ASP), have been shown to outperform heuristic-search-based approaches, such as conflict-based search (CBS). In this paper, we propose a new Boolean encoding for MAPF, and show how to implement it in ASP and MaxSAT. A feature that distinguishes our encoding from existing ones is that swap and follow conflicts are encoded using binary clauses, which can be exploited by current conflict-driven clause learning (CDCL) solvers. In addition, the number of clauses used to encode swap and follow conflicts do not depend on the number of agents, allowing us to scale better. For MaxSAT, we study different ways in which we may combine the MSU3 and LSU algorithms for maximum performance. In our experimental evaluation, we used square grids, ranging from 20 x 20 to 50 x 50 cells, and warehouse maps, with a varying number of agents and obstacles. We compared against representative solvers of the state-of-the-art, including the search-based algorithm CBS, the ASP-based solver ASP-MAPF, and the branch-and-cut-and-price hybrid solver, BCP. We observe that the ASP implementation of our encoding, ASP-MAPF2 outperforms other solvers in most of our experiments. The MaxSAT implementation of our encoding, MtMS shows best performance in relatively small warehouse maps when the number of agents is large, which are the instances with closer resemblance to hard puzzle-like problems.