Markov decision processes (MDPs) are formal models commonly used in sequential decision-making. MDPs capture the stochasticity that may arise, for instance, from imprecise actuators via probabilities in the transition function. However, in data-driven applications, deriving precise probabilities from (limited) data introduces statistical errors that may lead to unexpected or undesirable outcomes. Uncertain MDPs (uMDPs) do not require precise probabilities but instead use so-called uncertainty sets in the transitions, accounting for such limited data. Tools from the formal verification community efficiently compute robust policies that provably adhere to formal specifications, like safety constraints, under the worst-case instance in the uncertainty set. We continuously learn the transition probabilities of an MDP in a robust anytime-learning approach that combines a dedicated Bayesian inference scheme with the computation of robust policies. In particular, our method (1) approximates probabilities as intervals, (2) adapts to new data that may be inconsistent with an intermediate model, and (3) may be stopped at any time to compute a robust policy on the uMDP that faithfully captures the data so far. Furthermore, our method is capable of adapting to changes in the environment. We show the effectiveness of our approach and compare it to robust policies computed on uMDPs learned by the UCRL2 reinforcement learning algorithm in an experimental evaluation on several benchmarks.

Generative Flow Networks or GFlowNets are related to Monte-Carlo Markov chain methods (as they sample from a distribution specified by an energy function), reinforcement learning (as they learn a policy to sample composed objects through a sequence of steps), generative models (as they learn to represent and sample from a distribution) and amortized variational methods (as they can be used to learn to approximate and sample from an otherwise intractable posterior, given a prior and a likelihood). They are trained to generate an object $x$ through a sequence of steps with probability proportional to some reward function $R(x)$ (or $\exp(-\mathcal{E}(x))$ with $\mathcal{E}(x)$ denoting the energy function), given at the end of the generative trajectory. Like for other RL settings where the reward is only given at the end, the efficiency of training and credit assignment may suffer when those trajectories are longer. With previous GFlowNet work, no learning was possible from incomplete trajectories (lacking a terminal state and the computation of the associated reward). In this paper, we consider the case where the energy function can be applied not just to terminal states but also to intermediate states. This is for example achieved when the energy function is additive, with terms available along the trajectory. We show how to reparameterize the GFlowNet state flow function to take advantage of the partial reward already accrued at each state. This enables a training objective that can be applied to update parameters even with incomplete trajectories. Even when complete trajectories are available, being able to obtain more localized credit and gradients is found to speed up training convergence, as demonstrated across many simulations.

HAIT requires close coordination between humans and AI teammates to work together towards a common goal [40]. Effective communication, prediction of teammates' actions, and high-level coordination are essential components of this collaborative effort. In this regard, the proactive behavior of AI-based systems and the communication thereof during collaboration is an important research topic concerning HAITs, e.g., see Horvitz et al. [8]. Proactivity can be defined as an AI's self-initiating, anticipatory behavior for contributing to effective and efficient task completion. It has been shown to be essential for human teamwork as it leads to higher job and team performance and is associated with leadership and innovation [3]. However, the design of adequate proactivity for AI-based systems to support humans is still an open question and a challenging topic. It is essential to study the impact of proactive system actions on the human-agent trust relationship and how to use information about an AI agent's perceived trustworthiness to model appropriate proactive dialog strategies for forming effective HAITs.

Dialogue state tracking (DST) aims to convert the dialogue history into dialogue states which consist of slot-value pairs. As condensed structural information memorizing all history information, the dialogue state in the last turn is typically adopted as the input for predicting the current state by DST models. However, these models tend to keep the predicted slot values unchanged, which is defined as state momentum in this paper. Specifically, the models struggle to update slot values that need to be changed and correct wrongly predicted slot values in the last turn. To this end, we propose MoNET to tackle state momentum via noise-enhanced training. First, the previous state of each turn in the training data is noised via replacing some of its slot values. Then, the noised previous state is used as the input to learn to predict the current state, improving the model's ability to update and correct slot values. Furthermore, a contrastive context matching framework is designed to narrow the representation distance between a state and its corresponding noised variant, which reduces the impact of noised state and makes the model better understand the dialogue history. Experimental results on MultiWOZ datasets show that MoNET outperforms previous DST methods. Ablations and analysis verify the effectiveness of MoNET in alleviating state momentum and improving anti-noise ability.

The paper concerns the $d$-dimensional stochastic approximation recursion, $$ \theta_{n+1}= \theta_n + \alpha_{n + 1} f(\theta_n, \Phi_{n+1}) $$ in which $\Phi$ is a geometrically ergodic Markov chain on a general state space $\textsf{X}$ with stationary distribution $\pi$, and $f:\Re^d\times\textsf{X}\to\Re^d$. The main results are established under a version of the Donsker-Varadhan Lyapunov drift condition known as (DV3), and a stability condition for the mean flow with vector field $\bar{f}(\theta)=\textsf{E}[f(\theta,\Phi)]$, with $\Phi\sim\pi$. (i) $\{ \theta_n\}$ is convergent a.s. and in $L_4$ to the unique root $\theta^*$ of $\bar{f}(\theta)$. (ii) A functional CLT is established, as well as the usual one-dimensional CLT for the normalized error. (iii) The CLT holds for the normalized version, $z_n{=:} \sqrt{n} (\theta^{\text{PR}}_n -\theta^*)$, of the averaged parameters, $\theta^{\text{PR}}_n {=:} n^{-1} \sum_{k=1}^n\theta_k$, subject to standard assumptions on the step-size. Moreover, the normalized covariance converges, $$ \lim_{n \to \infty} n \textsf{E} [ {\widetilde{\theta}}^{\text{ PR}}_n ({\widetilde{\theta}}^{\text{ PR}}_n)^T ] = \Sigma_\theta^*,\;\;\;\textit{with $\widetilde{\theta}^{\text{ PR}}_n = \theta^{\text{ PR}}_n -\theta^*$,} $$ where $\Sigma_\theta^*$ is the minimal covariance of Polyak and Ruppert. (iv) An example is given where $f$ and $\bar{f}$ are linear in $\theta$, and the Markov chain $\Phi$ is geometrically ergodic but does not satisfy (DV3). While the algorithm is convergent, the second moment is unbounded: $ \textsf{E} [ \| \theta_n \|^2 ] \to \infty$ as $n\to\infty$.

Inverse Reinforcement Learning (IRL) is a compelling technique for revealing the rationale underlying the behavior of autonomous agents. IRL seeks to estimate the unknown reward function of a Markov decision process (MDP) from observed agent trajectories. However, IRL needs a transition function, and most algorithms assume it is known or can be estimated in advance from data. It therefore becomes even more challenging when such transition dynamics is not known a-priori, since it enters the estimation of the policy in addition to determining the system's evolution. When the dynamics of these agents in the state-action space is described by stochastic differential equations (SDE) in It^{o} calculus, these transitions can be inferred from the mean-field theory described by the Fokker-Planck (FP) equation. We conjecture there exists an isomorphism between the time-discrete FP and MDP that extends beyond the minimization of free energy (in FP) and maximization of the reward (in MDP). We identify specific manifestations of this isomorphism and use them to create a novel physics-aware IRL algorithm, FP-IRL, which can simultaneously infer the transition and reward functions using only observed trajectories. We employ variational system identification to infer the potential function in FP, which consequently allows the evaluation of reward, transition, and policy by leveraging the conjecture. We demonstrate the effectiveness of FP-IRL by applying it to a synthetic benchmark and a biological problem of cancer cell dynamics, where the transition function is inaccessible.

Process Mining (PM) is a consolidated discipline grounded on data mining and business process management. The exploitation of traditional PM tasks (discovery, conformance checking, and enhancement) is today a reality in many organizations [1, 2]. In the last decade, a wave of new results in artificial intelligence has triggered the interest of the PM research community in using supervised or unsupervised Machine Learning (ML) techniques for gaining insight into business processes and providing advice on how to improve their inefficiencies. In today's practice, ML models are routinely integrated into PM data pipelines [3] to carry out tasks like data transformation, noise reduction, anomaly detection, classification, and prediction. For example, ML is playing a key role in the interface between PM and sensor platforms. Advances in sensing technologies have made it possible to deploy distributed monitoring platforms capable of detecting fine-grained events. The granularity gap between these events and the activities considered by classic PM analysis has often been bridged using ML models [4, 5] that compute virtual activity logs, a problem which is also known as log lifting [6].

We study the sequential decision-making problem of allocating a limited resource to agents that reveal their stochastic demands on arrival over a finite horizon. Our goal is to design fair allocation algorithms that exhaust the available resource budget. This is challenging in sequential settings where information on future demands is not available at the time of decision-making. We formulate the problem as a discrete time Markov decision process (MDP). We propose a new algorithm, SAFFE, that makes fair allocations with respect to the entire demands revealed over the horizon by accounting for expected future demands at each arrival time. The algorithm introduces regularization which enables the prioritization of current revealed demands over future potential demands depending on the uncertainty in agents' future demands. Using the MDP formulation, we show that SAFFE optimizes allocations based on an upper bound on the Nash Social Welfare fairness objective, and we bound its gap to optimality with the use of concentration bounds on total future demands. Using synthetic and real data, we compare the performance of SAFFE against existing approaches and a reinforcement learning policy trained on the MDP. We show that SAFFE leads to more fair and efficient allocations and achieves close-to-optimal performance in settings with dense arrivals.

Restricted Boltzmann Machines are generative models that consist of a layer of hidden variables connected to another layer of visible units, and they are used to model the distribution over visible variables. In order to gain a higher representability power, many hidden units are commonly used, which, in combination with a large number of visible units, leads to a high number of trainable parameters. In this work we introduce the Structural Restricted Boltzmann Machine model, which taking advantage of the structure of the data in hand, constrains connections of hidden units to subsets of visible units in order to reduce significantly the number of trainable parameters, without compromising performance. As a possible area of application, we focus on image modelling. Based on the nature of the images, the structure of the connections is given in terms of spatial neighbourhoods over the pixels of the image that constitute the visible variables of the model. We conduct extensive experiments on various image domains. Image denoising is evaluated with corrupted images from the MNIST dataset. The generative power of our models is compared to vanilla RBMs, as well as their classification performance, which is assessed with five different image domains. Results show that our proposed model has a faster and more stable training, while also obtaining better results compared to an RBM with no constrained connections between its visible and hidden units.

In reinforcement learning (RL), state representations are key to dealing with large or continuous state spaces. While one of the promises of deep learning algorithms is to automatically construct features well-tuned for the task they try to solve, such a representation might not emerge from end-to-end training of deep RL agents. To mitigate this issue, auxiliary objectives are often incorporated into the learning process and help shape the learnt state representation. Bootstrapping methods are today's method of choice to make these additional predictions. Yet, it is unclear which features these algorithms capture and how they relate to those from other auxiliary-task-based approaches. In this paper, we address this gap and provide a theoretical characterization of the state representation learnt by temporal difference learning (Sutton, 1988). Surprisingly, we find that this representation differs from the features learned by Monte Carlo and residual gradient algorithms for most transition structures of the environment in the policy evaluation setting. We describe the efficacy of these representations for policy evaluation, and use our theoretical analysis to design new auxiliary learning rules. We complement our theoretical results with an empirical comparison of these learning rules for different cumulant functions on classic domains such as the four-room domain (Sutton et al, 1999) and Mountain Car (Moore, 1990).