Media streaming is the dominant application over wireless edge (access) networks. The increasing softwarization of such networks has led to efforts at intelligent control, wherein application-specific actions may be dynamically taken to enhance the user experience. The goal of this work is to develop and demonstrate learning-based policies for optimal decision making to determine which clients to dynamically prioritize in a video streaming setting. We formulate the policy design question as a constrained Markov decision problem (CMDP), and observe that by using a Lagrangian relaxation we can decompose it into single-client problems. Further, the optimal policy takes a threshold form in the video buffer length, which enables us to design an efficient constrained reinforcement learning (CRL) algorithm to learn it. Specifically, we show that a natural policy gradient (NPG) based algorithm that is derived using the structure of our problem converges to the globally optimal policy. We then develop a simulation environment for training, and a real-world intelligent controller attached to a WiFi access point for evaluation. We empirically show that the structured learning approach enables fast learning. Furthermore, such a structured policy can be easily deployed due to low computational complexity, leading to policy execution taking only about 15$\mu$s. Using YouTube streaming experiments in a resource constrained scenario, we demonstrate that the CRL approach can increase quality of experience (QOE) by over 30\%.

Close and precise placement of irregularly shaped objects requires a skilled robotic system. Particularly challenging is the manipulation of objects that have sensitive top surfaces and a fixed set of neighbors. To avoid damaging the surface, they have to be grasped from the side, and during placement, their neighbor relations have to be maintained. In this work, we train a reinforcement learning agent that generates smooth end-effector motions to place objects as close as possible next to each other. During the placement, our agent considers neighbor constraints defined in a given layout of the objects while trying to avoid collisions. Our approach learns to place compact object assemblies without the need for predefined spacing between objects as required by traditional methods. We thoroughly evaluated our approach using a two-finger gripper mounted to a robotic arm with six degrees of freedom. The results show that our agent outperforms two baseline approaches in terms of object assembly compactness, thereby reducing the needed space to place the objects according to the given neighbor constraints. On average, our approach reduces the distances between all placed objects by at least 60%, with fewer collisions at the same compactness compared to both baselines.

We study the constant regret guarantees in reinforcement learning (RL). Our objective is to design an algorithm that incurs only finite regret over infinite episodes with high probability. We introduce an algorithm, Cert-LSVI-UCB, for misspecified linear Markov decision processes (MDPs) where both the transition kernel and the reward function can be approximated by some linear function up to misspecification level $\zeta$. At the core of Cert-LSVI-UCB is an innovative certified estimator, which facilitates a fine-grained concentration analysis for multi-phase value-targeted regression, enabling us to establish an instance-dependent regret bound that is constant w.r.t. the number of episodes. Specifically, we demonstrate that for an MDP characterized by a minimal suboptimality gap $\Delta$, Cert-LSVI-UCB has a cumulative regret of $\tilde{\mathcal{O}}(d^3H^5/\Delta)$ with high probability, provided that the misspecification level $\zeta$ is below $\tilde{\mathcal{O}}(\Delta / (\sqrt{d}H^2))$. Remarkably, this regret bound remains constant relative to the number of episodes $K$. To the best of our knowledge, Cert-LSVI-UCB is the first algorithm to achieve a constant, instance-dependent, high-probability regret bound in RL with linear function approximation for infinite runs without relying on prior distribution assumptions. This not only highlights the robustness of Cert-LSVI-UCB to model misspecification but also introduces novel algorithmic designs and analytical techniques of independent interest.

As reinforcement learning techniques are increasingly applied to real-world decision problems, attention has turned to how these algorithms use potentially sensitive information. We consider the task of training a policy that maximizes reward while minimizing disclosure of certain sensitive state variables through the actions. We give examples of how this setting covers real-world problems in privacy for sequential decision-making. We solve this problem in the policy gradients framework by introducing a regularizer based on the mutual information (MI) between the sensitive state and the actions. We develop a model-based stochastic gradient estimator for optimization of privacy-constrained policies. We also discuss an alternative MI regularizer that serves as an upper bound to our main MI regularizer and can be optimized in a model-free setting, and a powerful direct estimator that can be used in an environment with differentiable dynamics. We contrast previous work in differentially-private RL to our mutual-information formulation of information disclosure. Experimental results show that our training method results in policies that hide the sensitive state, even in challenging high-dimensional tasks.

Reinforcement learning is a powerful framework aiming to determine optimal behavior in highly complex decision-making scenarios. This objective can be achieved using policy iteration, which requires to solve a typically large linear system of equations. We propose the variational quantum policy iteration (VarQPI) algorithm, realizing this step with a NISQ-compatible quantum-enhanced subroutine. Its scalability is supported by an analysis of the structure of generic reinforcement learning environments, laying the foundation for potential quantum advantage with utility-scale quantum computers. Furthermore, we introduce the warm-start initialization variant (WS-VarQPI) that significantly reduces resource overhead. The algorithm solves a large FrozenLake environment with an underlying 256x256-dimensional linear system, indicating its practical robustness.

Although visual navigation has been extensively studied using deep reinforcement learning, online learning for real-world robots remains a challenging task. Recent work directly learned from offline dataset to achieve broader generalization in the real-world tasks, which, however, faces the out-of-distribution (OOD) issue and potential robot localization failures in a given map for unseen observation. This significantly drops the success rates and even induces collision. In this paper, we present a self-correcting visual navigation method, SCALE, that can autonomously prevent the robot from the OOD situations without human intervention. Specifically, we develop an image-goal conditioned offline reinforcement learning method based on implicit Q-learning (IQL). When facing OOD observation, our novel localization recovery method generates the potential future trajectories by learning from the navigation affordance, and estimates the future novelty via random network distillation (RND). A tailored cost function searches for the candidates with the least novelty that can lead the robot to the familiar places. We collect offline data and conduct evaluation experiments in three real-world urban scenarios. Experiment results show that SCALE outperforms the previous state-of-the-art methods for open-world navigation with a unique capability of localization recovery, significantly reducing the need for human intervention. Code is available at https://github.com/KubeEdge4Robotics/ScaleNav.

Conventional trajectory planning approaches for autonomous racing are based on the sequential execution of prediction of the opposing vehicles and subsequent trajectory planning for the ego vehicle. If the opposing vehicles do not react to the ego vehicle, they can be predicted accurately. However, if there is interaction between the vehicles, the prediction loses its validity. For high interaction, instead of a planning approach that reacts exclusively to the fixed prediction, a trajectory planning approach is required that incorporates the interaction with the opposing vehicles. This paper demonstrates the limitations of a widely used conventional sampling-based approach within a highly interactive blocking scenario. We show that high success rates are achieved for less aggressive blocking behavior but that the collision rate increases with more significant interaction. We further propose a novel Reinforcement Learning (RL)-based trajectory planning approach for racing that explicitly exploits the interaction with the opposing vehicle without requiring a prediction. In contrast to the conventional approach, the RL-based approach achieves high success rates even for aggressive blocking behavior. Furthermore, we propose a novel safety layer (SL) that intervenes when the trajectory generated by the RL-based approach is infeasible. In that event, the SL generates a sub-optimal but feasible trajectory, avoiding termination of the scenario due to a not found valid solution.

Traditional search systems focus on query formulation for effective results but face challenges in scenarios such as product searches where crucial product details (e.g., size, color) remain concealed until users visit specific product pages. This highlights the need for intelligent web navigation agents capable of formulating queries and navigating web pages according to users' high-level intents. In response to this need, this work introduces a Grounded Language Agent for Intelligent Web Interactions, called GLAINTEL. Drawing upon advancements in language modeling and reinforcement learning, GLAINTEL investigates the efficacy of transformer-based models in enhancing the search capabilities of interactive web environments. Given the dynamic action space for each state in web navigation, GLAINTEL employs the Flan-T5 architecture and incorporates language modeling and value estimation heads. This work focuses on training smaller language models as agents across various scenarios, systematically evaluating the impact of human demonstrations on the training process. Specifically, we investigate scenarios where no human demonstrations are available and subsequently assess the effective utilization of such demonstrations. We also explore unsupervised domain adaptation for situations where demonstrations are confined to a specific domain. Experimental evaluations across diverse setups demonstrate the effectiveness of training agents in unsupervised settings, outperforming in-context learning-based approaches that employ larger models with up to 540 billion parameters. Surprisingly, behavioral cloning-based methods that straightforwardly use human demonstrations do not outperform unsupervised learning-based methods. Additionally, combining human demonstrations with Reinforcement Learning-based training yields results comparable to models utilizing GPT-4.

Adaptive bitrate (ABR) using conventional codecs cannot further modify the bitrate once a decision has been made, exhibiting limited adaptation capability. This may result in either overly conservative or overly aggressive bitrate selection, which could cause either inefficient utilization of the network bandwidth or frequent re-buffering, respectively. Neural representation for video (NeRV), which embeds the video content into neural network weights, allows video reconstruction with incomplete models. Specifically, the recovery of one frame can be achieved without relying on the decoding of adjacent frames. NeRV has the potential to provide high video reconstruction quality and, more importantly, pave the way for developing more flexible ABR strategies for video transmission. In this work, a new framework, named Evolutional Video streaming Adaptation via Neural representation (EVAN), which can adaptively transmit NeRV models based on soft actor-critic (SAC) reinforcement learning, is proposed. EVAN is trained with a more exploitative strategy and utilizes progressive playback to avoid re-buffering. Experiments showed that EVAN can outperform existing ABRs with 50% reduction in re-buffering and achieve nearly 20% .

Automating robotic surgery via learning from demonstration (LfD) techniques is extremely challenging. This is because surgical tasks often involve sequential decision-making processes with complex interactions of physical objects and have low tolerance for mistakes. Prior works assume that all demonstrations are fully observable and optimal, which might not be practical in the real world. This paper introduces a sample-efficient method that learns a robust reward function from a limited amount of ranked suboptimal demonstrations consisting of partial-view point cloud observations. The method then learns a policy by optimizing the learned reward function using reinforcement learning (RL). We show that using a learned reward function to obtain a policy is more robust than pure imitation learning. We apply our approach on a physical surgical electrocautery task and demonstrate that our method can perform well even when the provided demonstrations are suboptimal and the observations are high-dimensional point clouds. Code and videos available here: https://sites.google.com/view/lfdinelectrocautery