A robot providing mealtime assistance must perform specialized maneuvers with various utensils in order to pick up and feed a range of food items. Beyond these dexterous low-level skills, an assistive robot must also plan these strategies in sequence over a long horizon to clear a plate and complete a meal. Previous methods in robot-assisted feeding introduce highly specialized primitives for food handling without a means to compose them together. Meanwhile, existing approaches to long-horizon manipulation lack the flexibility to embed highly specialized primitives into their frameworks. We propose Visual Action Planning OveR Sequences (VAPORS), a framework for long-horizon food acquisition. VAPORS learns a policy for high-level action selection by leveraging learned latent plate dynamics in simulation. To carry out sequential plans in the real world, VAPORS delegates action execution to visually parameterized primitives. We validate our approach on complex real-world acquisition trials involving noodle acquisition and bimanual scooping of jelly beans. Across 38 plates, VAPORS acquires much more efficiently than baselines, generalizes across realistic plate variations such as toppings and sauces, and qualitatively appeals to user feeding preferences in a survey conducted across 49 individuals. Code, datasets, videos, and supplementary materials can be found on our website: https://sites.google.com/view/vaporsbot.

A recently popular approach to solving reinforcement learning is with data from human preferences. In fact, human preference data are now used with classic reinforcement learning algorithms such as actor-critic methods, which involve evaluating an intermediate policy over a reward learned from human preference data with distribution shift, known as off-policy evaluation (OPE). Such algorithm includes (i) learning reward function from human preference dataset, and (ii) learning expected cumulative reward of a target policy. Despite the huge empirical success, existing OPE methods with preference data often lack theoretical understanding and rely heavily on heuristics. In this paper, we study the sample efficiency of OPE with human preference and establish a statistical guarantee for it. Specifically, we approach OPE by learning the value function by fitted-Q-evaluation with a deep neural network. By appropriately selecting the size of a ReLU network, we show that one can leverage any low-dimensional manifold structure in the Markov decision process and obtain a sample-efficient estimator without suffering from the curse of high data ambient dimensionality. Under the assumption of high reward smoothness, our results \textit{almost align with the classical OPE results with observable reward data}. To the best of our knowledge, this is the first result that establishes a \textit{provably efficient} guarantee for off-policy evaluation with RLHF.

Compared to Markov Decision Processes (MDPs), learning in Partially Observable Markov Decision Processes (POMDPs) can be significantly harder due to the difficulty of interpreting observations. In this paper, we consider episodic learning problems in POMDPs with unknown transition and observation models. We consider the Posterior Sampling-based Reinforcement Learning (PSRL) algorithm for POMDPs and show that its Bayesian regret scales as the square root of the number of episodes. In general, the regret scales exponentially with the horizon length $H$, and we show that this is inevitable by providing a lower bound. However, under the condition that the POMDP is undercomplete and weakly revealing, we establish a polynomial Bayesian regret bound that improves the regret bound by a factor of $\Omega(H^2\sqrt{SA})$ over the recent result by arXiv:2204.08967.

The core principle of Variational Inference (VI) is to convert the statistical inference problem of computing complex posterior probability densities into a tractable optimization problem. This property enables VI to be faster than several sampling-based techniques. However, the traditional VI algorithm is not scalable to large data sets and is unable to readily infer out-of-bounds data points without re-running the optimization process. Recent developments in the field, like stochastic-, black box-, and amortized-VI, have helped address these issues. Generative modeling tasks nowadays widely make use of amortized VI for its efficiency and scalability, as it utilizes a parameterized function to learn the approximate posterior density parameters. In this paper, we review the mathematical foundations of various VI techniques to form the basis for understanding amortized VI. Additionally, we provide an overview of the recent trends that address several issues of amortized VI, such as the amortization gap, generalization issues, inconsistent representation learning, and posterior collapse. Finally, we analyze alternate divergence measures that improve VI optimization.

This thesis proposes and describes a research attempt at designing and developing a speaker independent spontaneous automatic speech recognition system for Tigrigna The acoustic model of the Speech Recognition System is developed using Carnegie Mellon University Automatic Speech Recognition development tool (Sphinx) while the SRIM tool is used for the development of the language model. Keywords Automatic Speech Recognition Tigrigna language

Traditional controllers have limitations as they rely on prior knowledge about the physics of the problem, require modeling of dynamics, and struggle to adapt to abnormal situations. Deep reinforcement learning has the potential to address these problems by learning optimal control policies through exploration in an environment. For safety-critical environments, it is impractical to explore randomly, and replacing conventional controllers with black-box models is also undesirable. Also, it is expensive in continuous state and action spaces, unless the search space is constrained. To address these challenges we propose a specialized deep residual policy safe reinforcement learning with a cycle of learning approach adapted for complex and continuous state-action spaces. Residual policy learning allows learning a hybrid control architecture where the reinforcement learning agent acts in synchronous collaboration with the conventional controller. The cycle of learning initiates the policy through the expert trajectory and guides the exploration around it. Further, the specialization through the input-output hidden Markov model helps to optimize policy that lies within the region of interest (such as abnormality), where the reinforcement learning agent is required and is activated. The proposed solution is validated on the Tennessee Eastman process control.

Resource allocation significantly impacts the performance of vehicle-to-everything (V2X) networks. Most existing algorithms for resource allocation are based on optimization or machine learning (e.g., reinforcement learning). In this paper, we explore resource allocation in a V2X network under the framework of federated reinforcement learning (FRL). On one hand, the usage of RL overcomes many challenges from the model-based optimization schemes. On the other hand, federated learning (FL) enables agents to deal with a number of practical issues, such as privacy, communication overhead, and exploration efficiency. The framework of FRL is then implemented by the inexact alternative direction method of multipliers (ADMM), where subproblems are solved approximately using policy gradients and accelerated by an adaptive step size calculated from their second moments. The developed algorithm, PASM, is proven to be convergent under mild conditions and has a nice numerical performance compared with some baseline methods for solving the resource allocation problem in a V2X network.

Over the past few years, the division of gait phases has emerged as a complex area of research that carries significant importance for various applications in the field of gait technologies. The accurate partitioning of gait phases plays a crucial role in advancing these applications. Researchers have been exploring a range of sensors that can be employed to provide data for algorithms involved in gait phase partitioning. These sensors can be broadly categorized into two types: wearable and non-wearable, each offering unique advantages and capabilities. In our study aimed at examining the current approaches to gait analysis and detection specifically designed for implementation in ambulatory rehabilitation systems, we conducted a comprehensive meta-analysis of existing research studies. Our analysis revealed a diverse range of sensors and sensor combinations that demonstrate the ability to analyze gait patterns in ambulatory settings. These sensor options vary from basic force-based binary switches to more intricate setups incorporating multiple inertial sensors and sophisticated algorithms. The findings highlight the wide spectrum of available technologies and methodologies used in gait analysis for ambulatory applications. To conduct an extensive review, we systematically examined two prominent databases, IEEE and Scopus, with the aim of identifying relevant studies pertaining to gait analysis. The search criteria were limited to 189 papers published between 1999 and 2023. From this pool, we identified and included five papers that specifically focused on various techniques including Thresholding, Quasi-static method, adaptive classifier, and SVM-based approaches. These selected papers provided valuable insights for our review.

The problem of system identification for the Kalman filter, relying on the expectation-maximization (EM) procedure to learn the underlying parameters of a dynamical system, has largely been studied assuming that observations are sampled at equally-spaced time points. However, in many applications this is a restrictive and unrealistic assumption. This paper addresses system identification for the continuous-discrete filter, with the aim of generalizing learning for the Kalman filter by relying on a solution to a continuous-time It\^o stochastic differential equation (SDE) for the latent state and covariance dynamics. We introduce a novel two-filter, analytical form for the posterior with a Bayesian derivation, which yields analytical updates which do not require the forward-pass to be pre-computed. Using this analytical and efficient computation of the posterior, we provide an EM procedure which estimates the parameters of the SDE, naturally incorporating irregularly sampled measurements. Generalizing the learning of latent linear dynamical systems (LDS) to continuous-time may extend the use of the hybrid Kalman filter to data which is not regularly sampled or has intermittent missing values, and can extend the power of non-linear system identification methods such as switching LDS (SLDS), which rely on EM for the linear discrete-time Kalman filter as a sub-unit for learning locally linearized behavior of a non-linear system. We apply the method by learning the parameters of a latent, multivariate Fokker-Planck SDE representing a toggle-switch genetic circuit using biologically realistic parameters, and compare the efficacy of learning relative to the discrete-time Kalman filter as the step-size irregularity and spectral-radius of the dynamics-matrix increases.

Robust Markov Decision Processes (MDPs) and risk-sensitive MDPs are both powerful tools for making decisions in the presence of uncertainties. Previous efforts have aimed to establish their connections, revealing equivalences in specific formulations. This paper introduces a new formulation for risk-sensitive MDPs, which assesses risk in a slightly different manner compared to the classical Markov risk measure (Ruszczy\'nski 2010), and establishes its equivalence with a class of regularized robust MDP (RMDP) problems, including the standard RMDP as a special case. Leveraging this equivalence, we further derive the policy gradient theorem for both problems, proving gradient domination and global convergence of the exact policy gradient method under the tabular setting with direct parameterization. This forms a sharp contrast to the Markov risk measure, known to be potentially non-gradient-dominant (Huang et al. 2021). We also propose a sample-based offline learning algorithm, namely the robust fitted-Z iteration (RFZI), for a specific regularized RMDP problem with a KL-divergence regularization term (or equivalently the risk-sensitive MDP with an entropy risk measure). We showcase its streamlined design and less stringent assumptions due to the equivalence and analyze its sample complexity.