Quadratic Assignment Problem (QAP) is a practical combinatorial optimization problems that has been studied for several years. Since it is NP-hard, solving large problem instances of QAP is challenging. Although heuristics can find semi-optimal solutions, the execution time significantly increases as the problem size increases. Recently, solving combinatorial optimization problems by deep learning has been attracting attention as a faster solver than heuristics. Even with deep learning, however, solving large QAP is still challenging. In this paper, we propose the deep reinforcement learning model called the two-stage graph pointer network (GPN) for solving QAP. Two-stage GPN relies on GPN, which has been proposed for Euclidean Traveling Salesman Problem (TSP). First, we extend GPN for general TSP, and then we add new algorithms to that model for solving QAP. Our experimental results show that our two-stage GPN provides semi-optimal solutions for benchmark problem instances from TSPlib and QAPLIB.

As autonomous driving technology rapidly advances, its potential to relieve drivers, enhance traffic efficiency, reduce energy consumption, and improve road safety is increasingly being recognized[1]. At present, advancements in autonomous vehicle control technologies are chiefly derived from the integration of Advanced Driver Assistance Systems (ADAS), including Adaptive Cruise Control (ACC), Lane Keeping Assistance Systems, and Lane Departure Warning technologies, which have been implemented in a variety of commercial electric vehicles. Projects such as Google's Waymo and Baidu's Apollo have advanced towards commercial operations, achieving autonomous driving capabilities and launching unmanned vehicle rental services in designated areas. The control framework of autonomous vehicles fundamentally encompasses three tiers: perception, planning, and control, with Figure 1 [2] depicting the comprehensive architecture of autonomous driving systems. The perception layer is tasked with the accurate perception and processing of measurement data to produce dependable state estimates essential for precise localization and environmental recognition.

In this work, we aim to teach robots to manipulate various thin-shell materials. Prior works studying thin-shell object manipulation mostly rely on heuristic policies or learn policies from real-world video demonstrations, and only focus on limited material types and tasks (e.g., cloth unfolding). However, these approaches face significant challenges when extended to a wider variety of thinshell materials and a diverse range of tasks. On the other hand, while virtual simulations are shown to be effective in diverse robot skill learning and evaluation, prior thin-shell simulation environments only support a subset of thin-shell materials, which also limits their supported range of tasks. To fill in this gap, we introduce ThinShellLab - a fully differentiable simulation platform tailored for robotic interactions with diverse thin-shell materials possessing varying material properties, enabling flexible thin-shell manipulation skill learning and evaluation. Building on top of our developed simulation engine, we design a diverse set of manipulation tasks centered around different thin-shell objects. Our experiments suggest that manipulating thin-shell objects presents several unique challenges: 1) thin-shell manipulation relies heavily on frictional forces due to the objects' co-dimensional nature, 2) the materials being manipulated are highly sensitive to minimal variations in interaction actions, and 3) the constant and frequent alteration in contact pairs makes trajectory optimization methods susceptible to local optima, and neither standard reinforcement learning algorithms nor trajectory optimization methods (either gradient-based or gradient-free) are able to solve the tasks alone. To overcome these challenges, we present an optimization scheme that couples sampling-based trajectory optimization and gradient-based optimization, boosting both learning efficiency and converged performance across various proposed tasks. By tuning simulation parameters with a minimal set of real-world data, we demonstrate successful deployment of the learned skills to real-robot settings. Manipulating thin-shell materials is complicated due to a diverse range of sophisticated activities involved in the manipulation process. For example, to lift an object using a sheet of paper, we would instinctively create a slight bend or curve in the paper before initiating the lift (Figure 1 (a)). Human beings intuitively learn such thin-shell manipulation skills, such as folding a paper to make a crease, drawing out a piece of sheet under a bottle, and even complicated card tricks. Compared with manipulating rigid bodies or volumetric materials, manipulating thin-shell materials poses several unique challenges. First, the physical forms of such materials are difficult to handle. For example, picking up a flat sheet is intrinsically difficult due to its close-to-zero thickness, preventing any effective grasping from the top.

Global Navigation Satellite Systems (GNSS)-based positioning plays a crucial role in various applications, including navigation, transportation, logistics, mapping, and emergency services. Traditional GNSS positioning methods are model-based and they utilize satellite geometry and the known properties of satellite signals. However, model-based methods have limitations in challenging environments and often lack adaptability to uncertain noise models. This paper highlights recent advances in Machine Learning (ML) and its potential to address these limitations. It covers a broad range of ML methods, including supervised learning, unsupervised learning, deep learning, and hybrid approaches. The survey provides insights into positioning applications related to GNSS such as signal analysis, anomaly detection, multi-sensor integration, prediction, and accuracy enhancement using ML. It discusses the strengths, limitations, and challenges of current ML-based approaches for GNSS positioning, providing a comprehensive overview of the field.

Reinforcement learning (RL) is a subset of artificial intelligence (AI) where agents learn the best action by interacting with the environment, making it suitable for tasks that do not require labeled data or direct supervision. Hyperparameters (HP) tuning refers to choosing the best parameter that leads to optimal solutions in RL algorithms. Manual or random tuning of the HP may be a crucial process because variations in this parameter lead to changes in the overall learning aspects and different rewards. In this paper, a novel and automatic HP-tuning method called Q-FOX is proposed. This uses both the FOX optimizer, a new optimization method inspired by nature that mimics red foxes' hunting behavior, and the commonly used, easy-to-implement RL Q-learning algorithm to solve the problem of HP tuning. Moreover, a new objective function is proposed which prioritizes the reward over the mean squared error (MSE) and learning time (steps). Q-FOX has been evaluated on two OpenAI Gym environment control tasks: Cart Pole and Frozen Lake. It exposed greater cumulative rewards than HP tuning with other optimizers, such as PSO, GA, Bee, or randomly selected HP. The cumulative reward for the Cart Pole task was 32.08, and for the Frozen Lake task was 0.95. Despite the robustness of Q-FOX, it has limitations. It cannot be used directly in real-word problems before choosing the HP in a simulation environment because its processes work iteratively, making it time-consuming. The results indicate that Q-FOX has played an essential role in HP tuning for RL algorithms to effectively solve different control tasks.

This paper designs novel nonparametric Bellman mappings in reproducing kernel Hilbert spaces (RKHSs) for reinforcement learning (RL). The proposed mappings benefit from the rich approximating properties of RKHSs, adopt no assumptions on the statistics of the data owing to their nonparametric nature, require no knowledge on transition probabilities of Markov decision processes, and may operate without any training data. Moreover, they allow for sampling on-the-fly via the design of trajectory samples, re-use past test data via experience replay, effect dimensionality reduction by random Fourier features, and enable computationally lightweight operations to fit into efficient online or time-adaptive learning. The paper offers also a variational framework to design the free parameters of the proposed Bellman mappings, and shows that appropriate choices of those parameters yield several popular Bellman-mapping designs. As an application, the proposed mappings are employed to offer a novel solution to the problem of countering outliers in adaptive filtering. More specifically, with no prior information on the statistics of the outliers and no training data, a policy-iteration algorithm is introduced to select online, per time instance, the ``optimal'' coefficient p in the least-mean-p-power-error method. Numerical tests on synthetic data showcase, in most of the cases, the superior performance of the proposed solution over several RL and non-RL schemes.

Optimizing techniques for discovering molecular structures with desired properties is crucial in artificial intelligence(AI)-based drug discovery. Combining deep generative models with reinforcement learning has emerged as an effective strategy for generating molecules with specific properties. Despite its potential, this approach is ineffective in exploring the vast chemical space and optimizing particular chemical properties. To overcome these limitations, we present Mol-AIR, a reinforcement learning-based framework using adaptive intrinsic rewards for effective goal-directed molecular generation. Mol-AIR leverages the strengths of both history-based and learning-based intrinsic rewards by exploiting random distillation network and counting-based strategies. In benchmark tests, Mol-AIR demonstrates superior performance over existing approaches in generating molecules with desired properties without any prior knowledge, including penalized LogP, QED, and celecoxib similarity. We believe that Mol-AIR represents a significant advancement in drug discovery, offering a more efficient path to discovering novel therapeutics.

This project aims to revolutionize drone flight control by implementing a nonlinear Deep Reinforcement Learning (DRL) agent as a replacement for traditional linear Proportional Integral Derivative (PID) controllers. The primary objective is to seamlessly transition drones between manual and autonomous modes, enhancing responsiveness and stability. We utilize the Proximal Policy Optimization (PPO) reinforcement learning strategy within the Gazebo simulator to train the DRL agent. Adding a $20,000 indoor Vicon tracking system offers <1mm positioning accuracy, which significantly improves autonomous flight precision. To navigate the drone in the shortest collision-free trajectory, we also build a 3 dimensional A* path planner and implement it into the real flight successfully.

We study evaluating a policy under best- and worst-case perturbations to a Markov decision process (MDP), given transition observations from the original MDP, whether under the same or different policy. This is an important problem when there is the possibility of a shift between historical and future environments, due to e.g. unmeasured confounding, distributional shift, or an adversarial environment. We propose a perturbation model that can modify transition kernel densities up to a given multiplicative factor or its reciprocal, which extends the classic marginal sensitivity model (MSM) for single time step decision making to infinite-horizon RL. We characterize the sharp bounds on policy value under this model, that is, the tightest possible bounds given by the transition observations from the original MDP, and we study the estimation of these bounds from such transition observations. We develop an estimator with several appealing guarantees: it is semiparametrically efficient, and remains so even when certain necessary nuisance functions such as worst-case Q-functions are estimated at slow nonparametric rates. It is also asymptotically normal, enabling easy statistical inference using Wald confidence intervals. In addition, when certain nuisances are estimated inconsistently we still estimate a valid, albeit possibly not sharp bounds on the policy value. We validate these properties in numeric simulations. The combination of accounting for environment shifts from train to test (robustness), being insensitive to nuisance-function estimation (orthogonality), and accounting for having only finite samples to learn from (inference) together leads to credible and reliable policy evaluation.

As mobile networks embrace the 5G era, the interest in adopting Reinforcement Learning (RL) algorithms to handle challenges in ultra-low-latency and high throughput scenarios increases. Simultaneously, the advent of packetized fronthaul networks imposes demanding requirements that traditional congestion control mechanisms cannot accomplish, highlighting the potential of RL-based congestion control algorithms. Although learning RL policies optimized for satisfying the stringent fronthaul requirements is feasible, the adoption of neural network models in real deployments still poses some challenges regarding real-time inference and interpretability. This paper proposes a methodology to deal with such challenges while maintaining the performance and generalization capabilities provided by a baseline RL policy. The method consists of (1) training a congestion control policy specialized in fronthaul-like networks via reinforcement learning, (2) collecting state-action experiences from the baseline, and (3) performing deep symbolic regression on the collected dataset. The proposed process overcomes the challenges related to inference-time limitations through closed-form expressions that approximate the baseline performance (link utilization, delay, and fairness) and which can be directly implemented in any programming language. Finally, we analyze the inner workings of the closed-form expressions.