Multi-agent Markov Decision Process (MMDP) has been an effective way of modelling sequential decision making algorithms for multi-agent cooperative environments. A number of algorithms based on centralized and decentralized planning have been developed in this domain. However, dynamically changing environment, coupled with exponential size of the state and joint action space, make it difficult for these algorithms to provide both efficiency and scalability. Recently, Centralized planning algorithm FV-MCTS-MP and decentralized planning algorithm \textit{Alternate maximization with Behavioural Cloning} (ABC) have achieved notable performance in solving MMDPs. However, they are not capable of adapting to dynamically changing environments and accounting for the lack of communication among agents, respectively. Against this background, we introduce a simulation based online planning algorithm, that we call SiCLOP, for multi-agent cooperative environments. Specifically, SiCLOP tailors Monte Carlo Tree Search (MCTS) and uses Coordination Graph (CG) and Graph Neural Network (GCN) to learn cooperation and provides real time solution of a MMDP problem. It also improves scalability through an effective pruning of action space. Additionally, unlike FV-MCTS-MP and ABC, SiCLOP supports transfer learning, which enables learned agents to operate in different environments. We also provide theoretical discussion about the convergence property of our algorithm within the context of multi-agent settings. Finally, our extensive empirical results show that SiCLOP significantly outperforms the state-of-the-art online planning algorithms.

We study the offline reinforcement learning (offline RL) problem, where the goal is to learn a reward-maximizing policy in an unknown Markov Decision Process (MDP) using the data coming from a policy $\mu$. In particular, we consider the sample complexity problems of offline RL for finite-horizon MDPs. Prior works study this problem based on different data-coverage assumptions, and their learning guarantees are expressed by the covering coefficients which lack the explicit characterization of system quantities. In this work, we analyze the Adaptive Pessimistic Value Iteration (APVI) algorithm and derive the suboptimality upper bound that nearly matches \[ O\left(\sum_{h=1}^H\sum_{s_h,a_h}d^{\pi^\star}_h(s_h,a_h)\sqrt{\frac{\mathrm{Var}_{P_{s_h,a_h}}{(V^\star_{h+1}+r_h)}}{d^\mu_h(s_h,a_h)}}\sqrt{\frac{1}{n}}\right). \] In complementary, we also prove a per-instance information-theoretical lower bound under the weak assumption that $d^\mu_h(s_h,a_h)>0$ if $d^{\pi^\star}_h(s_h,a_h)>0$. Different from the previous minimax lower bounds, the per-instance lower bound (via local minimaxity) is a much stronger criterion as it applies to individual instances separately. Here $\pi^\star$ is a optimal policy, $\mu$ is the behavior policy and $d_h^\mu$ is the marginal state-action probability. We call the above equation the intrinsic offline reinforcement learning bound since it directly implies all the existing optimal results: minimax rate under uniform data-coverage assumption, horizon-free setting, single policy concentrability, and the tight problem-dependent results. Later, we extend the result to the assumption-free regime (where we make no assumption on $ \mu$) and obtain the assumption-free intrinsic bound. Due to its generic form, we believe the intrinsic bound could help illuminate what makes a specific problem hard and reveal the fundamental challenges in offline RL.

In this paper, we propose a probabilistic physics-guided framework, termed Physics-guided Deep Markov Model (PgDMM). The framework is especially targeted to the inference of the characteristics and latent structure of nonlinear dynamical systems from measurement data, where it is typically intractable to perform exact inference of latent variables. A recently surfaced option pertains to leveraging variational inference to perform approximate inference. In such a scheme, transition and emission functions of the system are parameterized via feed-forward neural networks (deep generative models). However, due to the generalized and highly versatile formulation of neural network functions, the learned latent space is often prone to lack physical interpretation and structured representation. To address this, we bridge physics-based state space models with Deep Markov Models, thus delivering a hybrid modeling framework for unsupervised learning and identification for nonlinear dynamical systems. Specifically, the transition process can be modeled as a physics-based model enhanced with an additive neural network component, which aims to learn the discrepancy between the physics-based model and the actual dynamical system being monitored. The proposed framework takes advantage of the expressive power of deep learning, while retaining the driving physics of the dynamical system by imposing physics-driven restrictions on the side of the latent space. We demonstrate the benefits of such a fusion in terms of achieving improved performance on illustrative simulation examples and experimental case studies of nonlinear systems. Our results indicate that the physics-based models involved in the employed transition and emission functions essentially enforce a more structured and physically interpretable latent space, which is essential to generalization and prediction capabilities.

State abstraction enables sample-efficient learning and better task transfer in complex reinforcement learning environments. Recently, we proposed RePReL (Kokel et al. 2021), a hierarchical framework that leverages a relational planner to provide useful state abstractions for learning. We present a brief overview of this framework and the use of a dynamic probabilistic logic model to design these state abstractions. Our experiments show that RePReL not only achieves better performance and efficient learning on the task at hand but also demonstrates better generalization to unseen tasks.

The Common Agricultural Policy (CAP) is responsible for allocating agricultural subsidies in the European Union, which nears 50 billion euros each year [36]. Consequently, monitoring the crop types for subsidy allocation represents a significant challenge for payment agencies, which have encouraged the development of automated crop classification tools based on machine learning [24]. In particular, The Sentinels for Common Agricultural Policy (Sen4CAP) project [19] aims to provide EU member states with algorithmic solutions and best practice studies on crop monitoring based on satellite data from the Sentinel constellation [10]. Despite the inherent difficulty of differentiating between the complex growth patterns of plants, this task is made possible by the nearly limitless access to data and annotations. Indeed, Sentinel-2 offers multi-spectral observations at a high revisit time of five days on average, which are particularly appropriate for characterizing the complex spectral and temporal characteristics of crop phenology.

Global datasphere is increasing fast, and it is expected to reach 175 Zettabytes by 20251 . However, most of the content is unstructured and is not understandable by machines. Structuring this data into a knowledge graph enables multitudes of intelligent applications such as deep question answering, recommendation systems, semantic search, etc. The knowledge graph is an emerging technology that allows logical reasoning and uncovers new insights using content along with the context. Thereby, it provides necessary syntax and reasoning semantics that enable machines to solve complex healthcare, security, financial institutions, economics, and business problems. As an outcome, enterprises are putting their effort into constructing and maintaining knowledge graphs to support various downstream applications. Manual approaches are too expensive. Automated schemes can reduce the cost of building knowledge graphs up to 15-250 times. This paper critiques state-of-the-art automated techniques to produce knowledge graphs of near-human quality autonomously. Additionally, it highlights different research issues that need to be addressed to deliver high-quality knowledge graphs

Extreme events with potential deadly outcomes, such as those organized by terror groups, are highly unpredictable in nature and an imminent threat to society. In particular, quantifying the likelihood of a terror attack occurring in an arbitrary space-time region and its relative societal risk, would facilitate informed measures that would strengthen national security. This paper introduces a novel self-exciting marked spatio-temporal model for attacks whose inhomogeneous baseline intensity is written as a function of covariates. Its triggering intensity is succinctly modeled with a Gaussian Process prior distribution to flexibly capture intricate spatio-temporal dependencies between an arbitrary attack and previous terror events. By inferring the parameters of this model, we highlight specific space-time areas in which attacks are likely to occur. Furthermore, by measuring the outcome of an attack in terms of the number of casualties it produces, we introduce a novel mixture distribution for the number of casualties. This distribution flexibly handles low and high number of casualties and the discrete nature of the data through a {\it Generalized ZipF} distribution. We rely on a customized Markov chain Monte Carlo (MCMC) method to estimate the model parameters. We illustrate the methodology with data from the open source Global Terrorism Database (GTD) that correspond to attacks in Afghanistan from 2013-2018. We show that our model is able to predict the intensity of future attacks for 2019-2021 while considering various covariates of interest such as population density, number of regional languages spoken, and the density of population supporting the opposing government.

In this work we introduce a new framework for multi-objective Bayesian optimisation where the multi-objective functions can only be accessed via choice judgements, such as ``I pick options A,B,C among this set of five options A,B,C,D,E''. The fact that the option D is rejected means that there is at least one option among the selected ones A,B,C that I strictly prefer over D (but I do not have to specify which one). We assume that there is a latent vector function f for some dimension $n_e$ which embeds the options into the real vector space of dimension n, so that the choice set can be represented through a Pareto set of non-dominated options. By placing a Gaussian process prior on f and deriving a novel likelihood model for choice data, we propose a Bayesian framework for choice functions learning. We then apply this surrogate model to solve a novel multi-objective Bayesian optimisation from choice data problem.

In recent years, the transformer has established itself as a workhorse in many applications ranging from natural language processing to reinforcement learning. Similarly, Bayesian deep learning has become the gold-standard for uncertainty estimation in safety-critical applications, where robustness and calibration are crucial. Surprisingly, no successful attempts to improve transformer models in terms of predictive uncertainty using Bayesian inference exist. In this work, we study this curiously underpopulated area of Bayesian transformers. We find that weight-space inference in transformers does not work well, regardless of the approximate posterior. We also find that the prior is at least partially at fault, but that it is very hard to find well-specified weight priors for these models. We hypothesize that these problems stem from the complexity of obtaining a meaningful mapping from weight-space to function-space distributions in the transformer. Therefore, moving closer to function-space, we propose a novel method based on the implicit reparameterization of the Dirichlet distribution to apply variational inference directly to the attention weights. We find that this proposed method performs competitively with our baselines.

In this paper, we introduce a variational Bayesian algorithm (VBA) for image blind deconvolution. Our generic framework incorporates smoothness priors on the unknown blur/image and possible affine constraints (e.g., sum to one) on the blur kernel. One of our main contributions is the integration of VBA within a neural network paradigm, following an unrolling methodology. The proposed architecture is trained in a supervised fashion, which allows us to optimally set two key hyperparameters of the VBA model and lead to further improvements in terms of resulting visual quality. Various experiments involving grayscale/color images and diverse kernel shapes, are performed. The numerical examples illustrate the high performance of our approach when compared to state-of-the-art techniques based on optimization, Bayesian estimation, or deep learning.