Agents trained in simulation may make errors when performing actions in the real world due to mismatches between training and execution environments. These mistakes can be dangerous and difficult for the agent to discover because the agent is unable to predict them a priori. In this work, we propose the use of oracle feedback to learn a predictive model of these blind spots in order to reduce costly errors in real-world applications. We focus on blind spots in reinforcement learning (RL) that occur due to incomplete state representation: when the agent lacks necessary features to represent the true state of the world, and thus cannot distinguish between numerous states. We formalize the problem of discovering blind spots in RL as a noisy supervised learning problem with class imbalance. Our system learns models for predicting blind spots within unseen regions of the state space by combining techniques for label aggregation, calibration, and supervised learning. These models take into consideration noise emerging from different forms of oracle feedback, including demonstrations and corrections. We evaluate our approach across two domains and demonstrate that it achieves higher predictive performance than baseline methods, and also that the learned model can be used to selectively query an oracle at execution time to prevent errors. We also empirically analyze the biases of various feedback types and how these biases influence the discovery of blind spots. Further, we include analyses of our approach that incorporate relaxed initial optimality assumptions. (Interestingly, relaxing the assumptions of an optimal oracle and an optimal simulator policy helped our models to perform better.) We also propose extensions to our method that are intended to improve performance when using corrections and demonstrations data.

Human language and thought are characterized by the ability to systematically generate a potentially infinite number of complex structures (e.g., sentences) from a finite set of familiar components (e.g., words). Recent works in emergent communication have discussed the propensity of artificial agents to develop a systematically compositional language through playing co-operative referential games. The degree of structure in the input data was found to affect the compositionality of the emerged communication protocols. Thus, we explore various structural priors in multi-agent communication and propose a novel graph referential game. We compare the effect of structural inductive bias (bag-of-words, sequences and graphs) on the emergence of compositional understanding of the input concepts measured by topographic similarity and generalization to unseen combinations of familiar properties. We empirically show that graph neural networks induce a better compositional language prior and a stronger generalization to out-of-domain data. We further perform ablation studies that show the robustness of the emerged protocol in graph referential games.

The IVA solution leverages Interactions' Adaptive Understanding technology, which provides a blend of Artificial Intelligence (AI) and real-time …

The ultimate aim of artificial intelligence research is to develop agents with truly intelligent behaviors, akin to those found in humans and animals. To this end, a number of tools and techniques have been developed. In recent years, two approaches in particular - deep learning (DL) and reinforcement learning (RL), seem to have made considerable progress towards this goal. Both these fields have been widely studied, with numerous successful examples [22, 29, 42, 25, 40] reported, particularly in recent years. However, even with the unprecedented success of recent approaches such as deep RL [28, 27, 36], poor sample efficiency and limited generalization remain major concerns to be addressed, keeping in view the ultimate goal of developing general purpose agents. The poor generalization capability of DL is exposed by its liability to deception when presented with adversarial examples [30, 39]. Recent work [38], showed that it was possible to hurt the performance of DLbased image recognition systems by carefully altering just a single pixel.

We discuss an agent-based approach to proof design and implementation, which we call {\it Lemma Flow Diagram} (LFD). This approach is based on the multicut rule with $shared$ cuts. This approach is modular and easy to use, read and automate. Thus, we consider LFD an appealing alternative to `flow proof' which is popular in mathematical education. Some examples are provided.

A promising approach for teaching artificial agents to use natural language involves using human-in-the-loop training. However, recent work suggests that current machine learning methods are too data inefficient to be trained in this way from scratch. In this paper, we investigate the relationship between two categories of learning signals with the ultimate goal of improving sample efficiency: imitating human language data via supervised learning, and maximizing reward in a simulated multi-agent environment via self-play (as done in emergent communication), and introduce the term supervised self-play (S2P) for algorithms using both of these signals. We find that first training agents via supervised learning on human data followed by self-play outperforms the converse, suggesting that it is not beneficial to emerge languages from scratch. We then empirically investigate various S2P schedules that begin with supervised learning in two environments: a Lewis signaling game with symbolic inputs, and an image-based referential game with natural language descriptions. Lastly, we introduce population based approaches to S2P, which further improves the performance over single-agent methods.

We present the implementation of a new stochastic Kuramoto-Vicsek-type model for global optimization of nonconvex functions on the sphere. This model belongs to the class of Consensus-Based Optimization. In fact, particles move on the sphere driven by a drift towards an instantaneous consensus point, which is computed as a convex combination of particle locations, weighted by the cost function according to Laplace's principle, and it represents an approximation to a global minimizer. The dynamics is further perturbed by a random vector field to favor exploration, whose variance is a function of the distance of the particles to the consensus point. In particular, as soon as the consensus is reached the stochastic component vanishes. The main results of this paper are about the proof of convergence of the numerical scheme to global minimizers provided conditions of well-preparation of the initial datum. The proof combines previous results of mean-field limit with a novel asymptotic analysis, and classical convergence results of numerical methods for SDE. We present several numerical experiments, which show that the algorithm proposed in the present paper scales well with the dimension and is extremely versatile. To quantify the performances of the new approach, we show that the algorithm is able to perform essentially as good as ad hoc state of the art methods in challenging problems in signal processing and machine learning, namely the phase retrieval problem and the robust subspace detection.

-- Efficient driving in urban traffic scenarios requires foresight. The observation of other traffic participants, and the inference of their possible next actions depending on the own action is considered cooperative prediction and planning. Humans are well equipped with the capability to predict the actions of multiple interacting traffic participants and plan accordingly, without the need to directly communicate with others. Prior work has shown that it is possible to achieve effective cooperative planning without the need for explicit communication. However, the search space for cooperative plans is so large that the vast amount of the computational budget is spent on exploring the search space in unpromising regions that are far away from the solution. T o accelerate the planning process, we combined learned heuristics with a cooperative planning method in order to guide the search towards regions with promising actions, yielding better results at lower computational costs. Cooperative planning methods consider the mutual dependence of actions in multi-agent environments, opposed to methods that reduce multi-agent environments to single-agent environments, with other agents' action being independent of one another.

Existing simulations designed for cultural and interpersonal skill training rely on pre-defined responses with a menu option selection interface. Using a multiple-choice interface and restricting trainees' responses may limit the trainees' ability to apply the lessons in real life situations. This systems also uses a simplistic evaluation model, where trainees' selected options are marked as either correct or incorrect. This model may not capture sufficient information that could drive an adaptive feedback mechanism to improve trainees' cultural awareness. This paper describes the design of a dialogue-based simulation for cultural awareness training. The simulation, built around a disaster management scenario involving a joint coalition between the US and the Chinese armies. Trainees were able to engage in realistic dialogue with the Chinese agent. Their responses, at different points, get evaluated by different multi-label classification models. Based on training on our dataset, the models score the trainees' responses for cultural awareness in the Chinese culture. Trainees also get feedback that informs the cultural appropriateness of their responses. The result of this work showed the following; i) A feature-based evaluation model improves the design, modeling and computation of dialogue-based training simulation systems; ii) Output from current automatic speech recognition (ASR) systems gave comparable end results compared with the output from manual transcription; iii) A multi-label classification model trained as a cultural expert gave results which were comparable with scores assigned by human annotators.

To achieve a high learning accuracy, generative adversarial networks (GANs) must be fed by large datasets that adequately represent the data space. However, in many scenarios, the available datasets may be limited and distributed across multiple agents, each of which is seeking to learn the distribution of the data on its own. In such scenarios, the local datasets are inherently private and agents often do not wish to share them. In this paper, to address this multi-agent GAN problem, a novel brainstorming GAN (BGAN) architecture is proposed using which multiple agents can generate real-like data samples while operating in a fully distributed manner and preserving their data privacy. BGAN allows the agents to gain information from other agents without sharing their real datasets but by "brainstorming" via the sharing of their generated data samples. Therefore, the proposed BGAN yields a higher accuracy compared with a standalone GAN model and its architecture is fully distributed and does not need any centralized controller. Moreover, BGANs are shown to be scalable and not dependent on the hyperparameters of the agents' deep neural networks (DNNs) thus enabling the agents to have different DNN architectures. Theoretically, the interactions between BGAN agents are analyzed as a game whose unique Nash equilibrium is derived. Experimental results show that BGAN can generate real-like data samples with higher quality compared to other distributed GAN architectures.