Learning effective visual representations is crucial in open-world environments where agents encounter diverse and unstructured observations. This ability enables agents to extract meaningful information from raw sensory inputs, like pixels, which is essential for generalization across different tasks. However, evaluating representation learning separately from policy learning remains a challenge in most reinforcement learning (RL) benchmarks. To address this, we introduce the Sliding Puzzles Gym (SPGym), a benchmark that extends the classic 15-tile puzzle with variable grid sizes and observation spaces, including large real-world image datasets. SPGym allows scaling the representation learning challenge while keeping the latent environment dynamics and algorithmic problem fixed, providing a targeted assessment of agents' ability to form compositional and generalizable state representations. Our experiments with both model-free and model-based RL algorithms, with and without explicit representation learning components, show that as the representation challenge scales, SPGym effectively distinguishes agents based on their capabilities. Moreover, SPGym reaches difficulty levels where no tested algorithm consistently excels, highlighting key challenges and opportunities for advancing representation learning for decision-making research.

This paper presents a novel reinforcement learning framework for trajectory tracking of unmanned aerial vehicles in cluttered environments using a dual-agent architecture. Traditional optimization methods for trajectory tracking face significant computational challenges and lack robustness in dynamic environments. Our approach employs deep reinforcement learning (RL) to overcome these limitations, leveraging 3D pointcloud data to perceive the environment without relying on memory-intensive obstacle representations like occupancy grids. The proposed system features two RL agents: one for predicting UAV velocities to follow a reference trajectory and another for managing collision avoidance in the presence of obstacles. This architecture ensures real-time performance and adaptability to uncertainties. We demonstrate the efficacy of our approach through simulated and real-world experiments, highlighting improvements over state-of-the-art RL and optimization-based methods. Additionally, a curriculum learning paradigm is employed to scale the algorithms to more complex environments, ensuring robust trajectory tracking and obstacle avoidance in both static and dynamic scenarios.

Agent learning from human interaction often relies on explicit signals, but implicit social cues, such as prosody in speech, could provide valuable information for more effective learning. This paper advocates for the integration of prosody as a teaching signal to enhance agent learning from human teachers. Through two exploratory studies--one examining voice feedback in an interactive reinforcement learning setup and the other analyzing restricted audio from human demonstrations in three Atari games--we demonstrate that prosody carries significant information about task dynamics. Our findings suggest that prosodic features, when coupled with explicit feedback, can enhance reinforcement learning outcomes. Moreover, we propose guidelines for prosody-sensitive algorithm design and discuss insights into teaching behavior. Our work underscores the potential of leveraging prosody as an implicit signal for more efficient agent learning, thus advancing human-agent interaction paradigms.

Manipulation of deformable Linear objects (DLOs), including iron wire, rubber, silk, and nylon rope, is ubiquitous in daily life. These objects exhibit diverse physical properties, such as Young$'$s modulus and bending stiffness.Such diversity poses challenges for developing generalized manipulation policies. However, previous research limited their scope to single-material DLOs and engaged in time-consuming data collection for the state estimation. In this paper, we propose a two-stage manipulation approach consisting of a material property (e.g., flexibility) estimation and policy learning for DLO insertion with reinforcement learning. Firstly, we design a flexibility estimation scheme that characterizes the properties of different types of DLOs. The ground truth flexibility data is collected in simulation to train our flexibility estimation module. During the manipulation, the robot interacts with the DLOs to estimate flexibility by analyzing their visual configurations. Secondly, we train a policy conditioned on the estimated flexibility to perform challenging DLO insertion tasks. Our pipeline trained with diverse insertion scenarios achieves an 85.6% success rate in simulation and 66.67% in real robot experiments. Please refer to our project page: https://lmeee.github.io/DLOInsert/

Reinforcement learning (RL) is not yet competitive for many cyber-physical systems, such as robotics, process automation, and power systems, as training on a system with physical components cannot be accelerated, and simulation models do not exist or suffer from a large simulation-to-reality gap. During the long training time, expensive equipment cannot be used and might even be damaged due to inappropriate actions of the reinforcement learning agent. Our novel approach addresses exactly this problem: We train the reinforcement agent in a so-called shadow mode with the assistance of an existing conventional controller, which does not have to be trained and instantaneously performs reasonably well. In shadow mode, the agent relies on the controller to provide action samples and guidance towards favourable states to learn the task, while simultaneously estimating for which states the learned agent will receive a higher reward than the conventional controller. The RL agent will then control the system for these states and all other regions remain under the control of the existing controller. Over time, the RL agent will take over for an increasing amount of states, while leaving control to the baseline, where it cannot surpass its performance. Thus, we keep regret during training low and improve the performance compared to only using conventional controllers or reinforcement learning. We present and evaluate two mechanisms for deciding whether to use the RL agent or the conventional controller. The usefulness of our approach is demonstrated for a reach-avoid task, for which we are able to effectively train an agent, where standard approaches fail.

Effective governance and steering of behavior in complex multi-agent systems (MAS) are essential for managing system-wide outcomes, particularly in environments where interactions are structured by dynamic networks. In many applications, the goal is to promote pro-social behavior among agents, where network structure plays a pivotal role in shaping these interactions. This paper introduces a Hierarchical Graph Reinforcement Learning (HGRL) framework that governs such systems through targeted interventions in the network structure. Operating within the constraints of limited managerial authority, the HGRL framework demonstrates superior performance across a range of environmental conditions, outperforming established baseline methods. Our findings highlight the critical influence of agent-to-agent learning (social learning) on system behavior: under low social learning, the HGRL manager preserves cooperation, forming robust core-periphery networks dominated by cooperators. In contrast, high social learning accelerates defection, leading to sparser, chain-like networks. Additionally, the study underscores the importance of the system manager's authority level in preventing system-wide failures, such as agent rebellion or collapse, positioning HGRL as a powerful tool for dynamic network-based governance.

We introduce a framework that integrates variational autoencoders (VAE) with reinforcement learning (RL) to balance system performance and resource usage in multi-agent systems by dynamically adjusting network structures over time. A key innovation of this method is its capability to handle the vast action space of the network structure. This is achieved by combining Variational Auto-Encoder and Deep Reinforcement Learning to control the latent space encoded from the network structures. The proposed method, evaluated on the modified OpenAI particle environment under various scenarios, not only demonstrates superior performance compared to baselines but also reveals interesting strategies and insights through the learned behaviors.

While large models trained with self-supervised learning on offline datasets have shown remarkable capabilities in text and image domains, achieving the same generalisation for agents that act in sequential decision problems remains an open challenge. In this work, we take a step towards this goal by procedurally generating tens of millions of 2D physics-based tasks and using these to train a general reinforcement learning (RL) agent for physical control. To this end, we introduce Kinetix: an open-ended space of physics-based RL environments that can represent tasks ranging from robotic locomotion and grasping to video games and classic RL environments, all within a unified framework. Kinetix makes use of our novel hardware-accelerated physics engine Jax2D that allows us to cheaply simulate billions of environment steps during training. Our trained agent exhibits strong physical reasoning capabilities, being able to zero-shot solve unseen human-designed environments. Furthermore, fine-tuning this general agent on tasks of interest shows significantly stronger performance than training an RL agent *tabula rasa*. This includes solving some environments that standard RL training completely fails at. We believe this demonstrates the feasibility of large scale, mixed-quality pre-training for online RL and we hope that Kinetix will serve as a useful framework to investigate this further.

The industrial landscape is rapidly evolving with the advent of 6G applications, which demand massive connectivity, high computational capacity, and ultra-low latency. These requirements present new challenges, which can no longer be efficiently addressed by conventional strategies. In response, this article underscores the transformative potential of Deep Reinforcement Learning (DRL) for 6G, highlighting its advantages over classic machine learning solutions in meeting the demands of 6G. The necessity of DRL is further validated through three DRL applications in an end-to-end communication procedure, including wireless access control, baseband function placement, and network slicing coordination. However, DRL-based network management initiatives are far from mature. We extend the discussion to identify the challenges of applying DRL in practical networks and explore potential solutions along with their respective limitations. In the end, these insights are validated through a practical DRL deployment in managing network slices on the testbed.

In this study, we introduce Modular State-based Stackelberg Games (Mod-SbSG), a novel game structure developed for distributed self-learning in modular manufacturing systems. Mod-SbSG enhances cooperative decision-making among self-learning agents within production systems by integrating State-based Potential Games (SbPG) with Stackelberg games. This hierarchical structure assigns more important modules of the manufacturing system a first-mover advantage, while less important modules respond optimally to the leaders' decisions. This decision-making process differs from typical multi-agent learning algorithms in manufacturing systems, where decisions are made simultaneously. We provide convergence guarantees for the novel game structure and design learning algorithms to account for the hierarchical game structure. We further analyse the effects of single-leader/multiple-follower and multiple-leader/multiple-follower scenarios within a Mod-SbSG. To assess its effectiveness, we implement and test Mod-SbSG in an industrial control setting using two laboratory-scale testbeds featuring sequential and serial-parallel processes. The proposed approach delivers promising results compared to the vanilla SbPG, which reduces overflow by 97.1%, and in some cases, prevents overflow entirely. Additionally, it decreases power consumption by 5-13% while satisfying the production demand, which significantly improves potential (global objective) values.