With the growing popularity of deep reinforcement learning (DRL), human-in-the-loop (HITL) approach has the potential to revolutionize the way we approach decision-making problems and create new opportunities for human-AI collaboration. In this article, we introduce a novel multi-layered hierarchical HITL DRL algorithm that comprises three types of learning: self learning, imitation learning and transfer learning. In addition, we consider three forms of human inputs: reward, action and demonstration. Furthermore, we discuss main challenges, trade-offs and advantages of HITL in solving complex problems and how human information can be integrated in the AI solution systematically. To verify our technical results, we present a real-world unmanned aerial vehicles (UAV) problem wherein a number of enemy drones attack a restricted area. The objective is to design a scalable HITL DRL algorithm for ally drones to neutralize the enemy drones before they reach the area. To this end, we first implement our solution using an award-winning open-source HITL software called Cogment. We then demonstrate several interesting results such as (a) HITL leads to faster training and higher performance, (b) advice acts as a guiding direction for gradient methods and lowers variance, and (c) the amount of advice should neither be too large nor too small to avoid over-training and under-training. Finally, we illustrate the role of human-AI cooperation in solving two real-world complex scenarios, i.e., overloaded and decoy attacks.

This paper develops a model-based framework for continuous-time policy evaluation (CTPE) in reinforcement learning, incorporating both Brownian and L evy noise to model stochastic dynamics influenced by rare and extreme events. Our approach formulates the policy evaluation problem as solving a partial integro-differential equation (PIDE) for the value function with unknown coefficients. A key challenge in this setting is accurately recovering the unknown coefficients in the stochastic dynamics, particularly when driven by L evy processes with heavy tail effects. To address this, we propose a robust numerical approach that effectively handles both unbiased and censored trajectory datasets. This method combines maximum likelihood estimation with an iterative tail correction mechanism, improving the stability and accuracy of coefficient recovery. Additionally, we establish a theoretical bound for the policy evaluation error based on coefficient recovery error. Through numerical experiments, we demonstrate the effectiveness and robustness of our method in recovering heavy-tailed L evy dynamics and verify the theoretical error analysis in policy evaluation.

Soft continuum arms (SCAs) are increasingly recognized for their ability to safely and effectively interact with complex, unstructured environments. Their ability to conform and apply gentle forces makes them ideal for tasks such as handling delicate objects or working in close proximity to humans [Chen et al., 2022, Zongxing et al., 2020, Banerjee et al., 2018, Chen et al., 2021, V enter and Dirven, 2017]. However, their soft and deformable nature introduces challenges for modeling and control. Learning-enabled methods, such as model-free reinforcement learning (RL), offer a promising solution by learning behaviors directly from data rather than relying on analytically derived models [Falotico et al., 2024]. Despite these advantages, one of the primary obstacles to deploying SCAs in real-world is the sim-to-real transfer, where policies trained in simulation fail to generalize well on physical systems.

Packing objects efficiently is a fundamental problem in logistics, warehouse automation, and robotics. While traditional packing solutions focus on geometric optimization, packing irregular, 3D objects presents significant challenges due to variations in shape and stability. Reinforcement Learning~(RL) has gained popularity in robotic packing tasks, but training purely from simulation can be inefficient and computationally expensive. In this work, we propose HERB, a human-augmented RL framework for packing irregular objects. We first leverage human demonstrations to learn the best sequence of objects to pack, incorporating latent factors such as space optimization, stability, and object relationships that are difficult to model explicitly. Next, we train a placement algorithm that uses visual information to determine the optimal object positioning inside a packing container. Our approach is validated through extensive performance evaluations, analyzing both packing efficiency and latency. Finally, we demonstrate the real-world feasibility of our method on a robotic system. Experimental results show that our method outperforms geometric and purely RL-based approaches by leveraging human intuition, improving both packing robustness and adaptability. This work highlights the potential of combining human expertise-driven RL to tackle complex real-world packing challenges in robotic systems.

Introduction to Quantum Machine Learning and Quantum Architecture Search Samuel Y en-Chi Chen 1 Zhiding Liang 2 1 Wells Fargo 2 Rensselaer Polytechnic Institute Abstract --Recent advancements in quantum computing (QC) and machine learning (ML) have fueled significant research efforts aimed at integrating these two transformative technologies. Quantum machine learning (QML), an emerging interdisciplinary field, leverages quantum principles to enhance the performance of ML algorithms. Concurrently, the exploration of systematic and automated approaches for designing high-performance quantum circuit architectures for QML tasks has gained prominence, as these methods empower researchers outside the quantum computing domain to effectively utilize quantum-enhanced tools. This tutorial will provide an in-depth overview of recent breakthroughs in both areas, highlighting their potential to expand the application landscape of QML across diverse fields. I NTRODUCTION Quantum computing (QC) offers the potential for substantial speedups in solving certain computationally challenging problems compared to classical computers. Recent advancements in quantum hardware, coupled with remarkable progress in classical AI and machine learning (ML) techniques, have sparked growing interest in merging these two technologies to further accelerate advancements in artificial intelligence.

In safe reinforcement learning (RL), auxiliary safety costs are used to align the agent to safe decision making. In practice, safety constraints, including cost functions and budgets, are unknown or hard to specify, as it requires anticipation of all possible unsafe behaviors. We therefore address a general setting where the true safety definition is unknown, and has to be learned from sparsely labeled data. Our key contributions are: first, we design a safety model that performs credit assignment to estimate each decision step's impact on the overall safety using a dataset of diverse trajectories and their corresponding binary safety labels (i.e., whether the corresponding trajectory is safe/unsafe). Second, we illustrate the architecture of our safety model to demonstrate its ability to learn a separate safety score for each timestep. Third, we reformulate the safe RL problem using the proposed safety model and derive an effective algorithm to optimize a safe yet rewarding policy. Finally, our empirical results corroborate our findings and show that this approach is effective in satisfying unknown safety definition, and scalable to various continuous control tasks.

The examples are nothing if not relatable: preparing breakfast, or playing a game of chess or tic-tac-toe. Yet the idea of learning from the environment and taking steps that progress toward a goal apparently was under-studied when ACM A.M. Turing Award recipients Andrew G. Barto and Richard S. Sutton took on the topic in the late 1970s. Eventually, their research led to the creation of reinforcement learning algorithms that sought not to recognize patterns but maximize rewards. Barto and Sutton spoke about how it all unfolded, and what's next for the techniques that are so celebrated for their success in AlphaGo and AlphaZero. Let's start with the earliest days of your collaboration.

As an undergraduate at Stanford University in the mid-1970s, Richard Sutton pored through the school's library, trying to read everything he could about learning and machine intelligence. What he found disappointed him, because he did not think it really got to the heart of the matter. "It was mostly pattern recognition. It was mostly learning from examples. And I knew from psychology that animals do very different things," Sutton said.

We consider the problem of non-stationary reinforcement learning (RL) in the infinite-horizon average-reward setting. We model it by a Markov Decision Process with time-varying rewards and transition probabilities, with a variation budget of $\Delta_T$. Existing non-stationary RL algorithms focus on model-based and model-free value-based methods. Policy-based methods despite their flexibility in practice are not theoretically well understood in non-stationary RL. We propose and analyze the first model-free policy-based algorithm, Non-Stationary Natural Actor-Critic (NS-NAC), a policy gradient method with a restart based exploration for change and a novel interpretation of learning rates as adapting factors. Further, we present a bandit-over-RL based parameter-free algorithm BORL-NS-NAC that does not require prior knowledge of the variation budget $\Delta_T$. We present a dynamic regret of $\tilde{\mathscr O}(|S|^{1/2}|A|^{1/2}\Delta_T^{1/6}T^{5/6})$ for both algorithms, where $T$ is the time horizon, and $|S|$, $|A|$ are the sizes of the state and action spaces. The regret analysis leverages a novel adaptation of the Lyapunov function analysis of NAC to dynamic environments and characterizes the effects of simultaneous updates in policy, value function estimate and changes in the environment.

With the exponential growth of Internet of Things (IoT) devices, edge computing (EC) is gradually playing an important role in providing cost-effective services. However, existing approaches struggle to perform well in graph-structured scenarios where user data is correlated, such as traffic flow prediction and social relationship recommender systems. In particular, graph neural network (GNN)-based approaches lead to expensive server communication cost. To address this problem, we propose GraphEdge, an efficient GNN-based EC architecture. It considers the EC system of GNN tasks, where there are associations between users and it needs to take into account the task data of its neighbors when processing the tasks of a user. Specifically, the architecture first perceives the user topology and represents their data associations as a graph layout at each time step. Then the graph layout is optimized by calling our proposed hierarchical traversal graph cut algorithm (HiCut), which cuts the graph layout into multiple weakly associated subgraphs based on the aggregation characteristics of GNN, and the communication cost between different subgraphs during GNN inference is minimized. Finally, based on the optimized graph layout, our proposed deep reinforcement learning (DRL) based graph offloading algorithm (DRLGO) is executed to obtain the optimal offloading strategy for the tasks of users, the offloading strategy is subgraph-based, it tries to offload user tasks in a subgraph to the same edge server as possible while minimizing the task processing time and energy consumption of the EC system. Experimental results show the good effectiveness and dynamic adaptation of our proposed architecture and it also performs well even in dynamic scenarios.