Stochastic planning can be reduced to probabilistic inference in large discrete graphical models, but hardness of inference requires approximation schemes to be used. In this paper we argue that such applications can be disentangled along two dimensions. The first is the direction of information flow in the idealized exact optimization objective, i.e., forward vs backward inference. The second is the type of approximation used to compute this objective, e.g., Belief Propagation (BP) vs mean field variational inference (MFVI). This new categorization allows us to unify a large amount of isolated efforts in prior work explaining their connections and differences as well as potential improvements. An extensive experimental evaluation over large stochastic planning problems shows the advantage of forward BP over several algorithms based on MFVI. An analysis of practical limitations of MFVI motivates a novel algorithm, collapsed state variational inference (CSVI), which provides a tighter approximation and achieves comparable planning performance with forward BP.

Machine Learning (ML) is a predominant tool nowadays to solve several challenges in different industries, such as credit scoring Provenzano et al. [2020], fraud analysis Tiwari et al. [2021], product recommendation Rohde et al. [2018], and demand forecasting Masini et al. [2020], among other extensively explored use cases. Under this premise, the research of the quantum computing properties applied to ML has expanded rapidly in recent years since a proven advantage could be a highly useful cross-industry. The recent progress of these explorations in Quantum Machine Learning (QML) Mishra et al. [2021] put a spotlight on quantum technology, introducing a challenge to determine if QML will provide an advantage over classical machine learning or not. The actual devices are noisy, meaning that the depth or consecutive gate operations are limited [Ristè et al., 2013, Burnett et al., 2019, Wang et al., 2021]. Qubits will lose their entanglement and so, the information. These devices make up the NISQ era Preskill [2018] and limit the use of quantum algorithms or hybrid algorithms to be useful Callison and Chancellor [2022].

Structural causal models (SCMs) provide a principled approach to identifying causation from observational and experimental data in disciplines ranging from economics to medicine. However, SCMs, which is typically represented as graphical models, cannot rely only on data, rather require support of domain knowledge. A key challenge in this context is the absence of a methodological framework for encoding priors (background knowledge) into causal models in a systematic manner. We propose an abstraction called causal knowledge hierarchy (CKH) for encoding priors into causal models. Our approach is based on the foundation of "levels of evidence" in medicine, with a focus on confidence in causal information. Using CKH, we present a methodological framework for encoding causal priors from various information sources and combining them to derive an SCM. We evaluate our approach on a simulated dataset and demonstrate overall performance compared to the ground truth causal model with sensitivity analysis.

We study cooperative online learning in stochastic and adversarial Markov decision process (MDP). That is, in each episode, $m$ agents interact with an MDP simultaneously and share information in order to minimize their individual regret. We consider environments with two types of randomness: \emph{fresh} -- where each agent's trajectory is sampled i.i.d, and \emph{non-fresh} -- where the realization is shared by all agents (but each agent's trajectory is also affected by its own actions). More precisely, with non-fresh randomness the realization of every cost and transition is fixed at the start of each episode, and agents that take the same action in the same state at the same time observe the same cost and next state. We thoroughly analyze all relevant settings, highlight the challenges and differences between the models, and prove nearly-matching regret lower and upper bounds. To our knowledge, we are the first to consider cooperative reinforcement learning (RL) with either non-fresh randomness or in adversarial MDPs.

Intention deception involves computing a strategy which deceives the opponent into a wrong belief about the agent's intention or objective. This paper studies a class of probabilistic planning problems with intention deception and investigates how a defender's limited sensing modality can be exploited by an attacker to achieve its attack objective almost surely (with probability one) while hiding its intention. In particular, we model the attack planning in a stochastic system modeled as a Markov decision process (MDP). The attacker is to reach some target states while avoiding unsafe states in the system and knows that his behavior is monitored by a defender with partial observations. Given partial state observations for the defender, we develop qualitative intention deception planning algorithms that construct attack strategies to play against an action-visible defender and an action-invisible defender, respectively. The synthesized attack strategy not only ensures the attack objective is satisfied almost surely but also deceives the defender into believing that the observed behavior is generated by a normal/legitimate user and thus failing to detect the presence of an attack. We show the proposed algorithms are correct and complete and illustrate the deceptive planning methods with examples.

Why is ordinary language vague? We argue that in contexts in which a cooperative speaker is not perfectly informed about the world, the use of vague expressions can offer an optimal tradeoff between truthfulness (Gricean Quality) and informativeness (Gricean Quantity). Focusing on expressions of approximation such as "around", which are semantically vague, we show that they allow the speaker to convey indirect probabilistic information, in a way that can give the listener a more accurate representation of the information available to the speaker than any more precise expression would (intervals of the form "between"). That is, vague sentences can be more informative than their precise counterparts. We give a probabilistic treatment of the interpretation of "around", and offer a model for the interpretation and use of "around"-statements within the Rational Speech Act (RSA) framework. In our account the shape of the speaker's distribution matters in ways not predicted by the Lexical Uncertainty model standardly used in the RSA framework for vague predicates. We use our approach to draw further lessons concerning the semantic flexibility of vague expressions and their irreducibility to more precise meanings.

Abstract--Deep reinforcement learning has achieved great success in laser-based collision avoidance works because the laser can sense accurate depth information without too much redundant data, which can maintain the robustness of the algorithm when it is migrated from the simulation environment to the real world. However, high-cost laser devices are not only difficult to deploy for a large scale of robots but also demonstrate unsatisfactory robustness towards the complex obstacles, including irregular obstacles, e.g., tables, chairs, and shelves, as well as complex ground and special materials. In this paper, we propose a novel monocular camera-based complex obstacle avoidance framework. Particularly, we innovatively transform the captured RGB images to pseudo-laser measurements for efficient deep reinforcement learning. Compared to the traditional laser measurement captured at a certain height that only contains one-dimensional distance information away from the neighboring obstacles, our proposed pseudo-laser measurement fuses the depth and semantic information of the captured RGB image, which makes our method effective for complex obstacles. We also design a feature extraction guidance module to weight the input pseudo-laser measurement, and the agent has more reasonable attention for the current state, which is conducive to improving the accuracy and efficiency of the obstacle avoidance policy. Besides, we adaptively add the synthesized noise to the laser measurement during the training stage to decrease the simto-real gap and increase the robustness of our model in the real environment. Finally, the experimental results show that our framework achieves state-of-the-art performance in several virtual and real-world scenarios. J. Ding is with the School of Computer Science, Dalian University Figure 1. One-dimensional laser sensors have low robustness to the complex of Technology, Dalian 116024, China, and also with Hebei University of obstacles of certain types.

We are assisting at a growing interest in the development of learning architectures with application to digital communication systems. Herein, we consider the detection/decoding problem. We aim at developing an optimal neural architecture for such a task. The definition of the optimal criterion is a fundamental step. We propose to use the mutual information (MI) of the channel input-output signal pair, which yields to the minimization of the a-posteriori information of the transmitted codeword given the communication channel output observation. The computation of the a-posteriori information is a formidable task, and for the majority of channels it is unknown. Therefore, it has to be learned. For such an objective, we propose a novel neural estimator based on a discriminative formulation. This leads to the derivation of the mutual information neural decoder (MIND). The developed neural architecture is capable not only to solve the decoding problem in unknown channels, but also to return an estimate of the average MI achieved with the coding scheme, as well as the decoding error probability. Several numerical results are reported and compared with maximum a-posteriori and maximum likelihood decoding strategies.

We consider the problem of detecting the presence of a signal in a rank-one spiked Wigner model. For general non-Gaussian noise, assuming that the signal is drawn from the Rademacher prior, we prove that the log likelihood ratio (LR) of the spiked model against the null model converges to a Gaussian when the signal-to-noise ratio is below a certain threshold. The threshold is optimal in the sense that the reliable detection is possible by a transformed principal component analysis (PCA) above it. From the mean and the variance of the limiting Gaussian for the log LR, we compute the limit of the sum of the Type-I error and the Type-II error of the likelihood ratio test. We also prove similar results for a rank-one spiked IID model where the noise is asymmetric but the signal is symmetric.

Particle filtering is a standard Monte-Carlo approach for a wide range of sequential inference tasks. The key component of a particle filter is a set of particles with importance weights that serve as a proxy of the true posterior distribution of some stochastic process. In this work, we propose continuous latent particle filters, an approach that extends particle filtering to the continuous-time domain. We demonstrate how continuous latent particle filters can be used as a generic plug-in replacement for inference techniques relying on a learned variational posterior. Our experiments with different model families based on latent neural stochastic differential equations demonstrate superior performance of continuous-time particle filtering in inference tasks like likelihood estimation and sequential prediction for a variety of stochastic processes.