Recent advances in robotic foundation models have enabled the development of generalist policies that can adapt to diverse tasks. While these models show impressive flexibility, their performance heavily depends on the quality of their training data. In this work, we propose Reinforcement Learning Distilled Generalists (RLDG), a method that leverages reinforcement learning to generate high-quality training data for finetuning generalist policies. Through extensive real-world experiments on precise manipulation tasks like connector insertion and assembly, we demonstrate that generalist policies trained with RL-generated data consistently outperform those trained with human demonstrations, achieving up to 40% higher success rates while generalizing better to new tasks. We also provide a detailed analysis that reveals this performance gain stems from both optimized action distributions and improved state coverage. Our results suggest that combining task-specific RL with generalist policy distillation offers a promising approach for developing more capable and efficient robotic manipulation systems that maintain the flexibility of foundation models while achieving the performance of specialized controllers. Videos and code can be found on our project website https://generalist-distillation.github.io

Abstract--With the growing demands for Autonomous Surface Vehicles (ASVs) in recent years, the number of ASVs being deployed for various maritime missions is expected to increase rapidly in the near future. However, it is still challenging for ASVs to perform sensor-based autonomous navigation in obstacle-filled and congested waterways, where perception errors, closely gathered vehicles and limited maneuvering space near buoys may cause difficulties in following the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs). To address these issues, we propose a novel Distributional Reinforcement Learning based navigation system that can work with onboard LiDAR and odometry sensors to generate arbitrary thrust commands in continuous action space. Comprehensive evaluations of the proposed system in highfidelity Gazebo simulations show its ability to decide whether to follow COLREGs or take other beneficial actions based on the scenarios encountered, offering superior performance in navigation safety and efficiency compared to systems using stateof-the-art Distributional RL, non-Distributional RL and classical methods. Figure 1: The proposed navigation system.

With the rapid development of artificial intelligence, robotics, and Internet of Things, multi-robot systems are progressively acquiring human-like environmental perception and understanding capabilities, empowering them to complete complex tasks through autonomous decision-making and interaction. However, the Internet of Robotic Things (IoRT) faces significant challenges in terms of spectrum resources, sensing accuracy, communication latency, and energy supply. To address these issues, a reconfigurable intelligent surface (RIS)-aided IoRT network is proposed to enhance the overall performance of robotic communication, sensing, computation, and energy harvesting. In the case studies, by jointly optimizing parameters such as transceiver beamforming, robot trajectories, and RIS coefficients, solutions based on multi-agent deep reinforcement learning and multi-objective optimization are proposed to solve problems such as beamforming design, path planning, target sensing, and data aggregation. Numerical results are provided to demonstrate the effectiveness of proposed solutions in improve communication quality, sensing accuracy, computation error, and energy efficiency of RIS-aided IoRT networks.

Deep reinforcement learning (DRL) has emerged as an innovative solution for controlling legged robots in challenging environments using minimalist architectures. Traditional control methods for legged robots, such as inverse dynamics, either directly manage joint torques or use proportional-derivative (PD) controllers to regulate joint positions at a higher level. In case of DRL, direct torque control presents significant challenges, leading to a preference for joint position control. However, this approach necessitates careful adjustment of joint PD gains, which can limit both adaptability and efficiency. In this paper, we propose GainAdaptor, an adaptive gain control framework that autonomously tunes joint PD gains to enhance terrain adaptability and energy efficiency. The framework employs a dual-actor algorithm to dynamically adjust the PD gains based on varying ground conditions. By utilizing a divided action space, GainAdaptor efficiently learns stable and energy-efficient locomotion. We validate the effectiveness of the proposed method through experiments conducted on a Unitree Go1 robot, demonstrating improved locomotion performance across diverse terrains.

Human cultural complexity did not arise in a vacuum. Scholars in the humanities and social sciences have long debated how ecological factors, such as climate and resource availability, enabled early hunter-gatherers to allocate time and energy beyond basic subsistence tasks. This paper presents a formal, interdisciplinary approach that integrates theoretical modeling with computational methods to examine whether conditions that allow lower spoilage of stored food, often associated with colder climates and abundant large fauna, could indirectly foster the emergence of cultural complexity. Our contribution is twofold. First, we propose a mathematical framework that relates spoilage rates, yield levels, resource management skills, and cultural activities. Under this framework, we prove that lower spoilage and adequate yields reduce the frequency of hunting, thus freeing substantial time for cultural pursuits. Second, we implement a reinforcement learning simulation, inspired by engineering optimization techniques, to validate the theoretical predictions. By training agents in different $(Y,p)$ environments, where $Y$ is yield and $p$ is the probability of daily spoilage, we observe patterns consistent with the theoretical model: stable conditions with lower spoilage strongly correlate with increased cultural complexity. While we do not claim to replicate prehistoric social realities directly, our results suggest that ecologically stable niches provided a milieu in which cultural forms could germinate and evolve. This study, therefore, offers an integrative perspective that unites humanistic inquiries into the origins of culture with the formal rigor and exploratory power of computational modeling.

Mixed service mode docks enhance efficiency by flexibly handling both loading and unloading trucks in warehouses. However, existing research often predetermines the number and location of these docks prior to planning truck assignment and sequencing. This paper proposes a new model integrating dock mode decision, truck assignment, and scheduling, thus enabling adaptive dock mode arrangements. Specifically, we introduce a Q-learning-based adaptive large neighborhood search (Q-ALNS) algorithm to address the integrated problem. The algorithm adjusts dock modes via perturbation operators, while truck assignment and scheduling are solved using destroy and repair local search operators. Q-learning adaptively selects these operators based on their performance history and future gains, employing the epsilon-greedy strategy. Extensive experimental results and statistical analysis indicate that the Q-ALNS benefits from efficient operator combinations and its adaptive mechanism, consistently outperforming benchmark algorithms in terms of optimality gap and Pareto front discovery. In comparison to the predetermined service mode, our adaptive strategy results in lower average tardiness and makespan, highlighting its superior adaptability to varying demands.

Simulation has become a crucial tool for Building Energy Optimization (BEO) as it enables the evaluation of different design and control strategies at a low cost. Machine Learning (ML) algorithms can leverage large-scale simulations to learn optimal control from vast amounts of data without supervision, particularly under the Reinforcement Learning (RL) paradigm. Unfortunately, the lack of open and standardized tools has hindered the widespread application of ML and RL to BEO. To address this issue, this paper presents Sinergym, an open-source Python-based virtual testbed for large-scale building simulation, data collection, continuous control, and experiment monitoring. Sinergym provides a consistent interface for training and running controllers, predefined benchmarks, experiment visualization and replication support, and comprehensive documentation in a ready-to-use software library. This paper 1) highlights the main features of Sinergym in comparison to other existing frameworks, 2) describes its basic usage, and 3) demonstrates its applicability for RL-based BEO through several representative examples. By integrating simulation, data, and control, Sinergym supports the development of intelligent, data-driven applications for more efficient and responsive building operations, aligning with the objectives of digital twin technology.

Federated learning (FL) enables collaborative learning among decentralized clients while safeguarding the privacy of their local data. Existing studies on FL typically assume offline labeled data available at each client when the training starts. Nevertheless, the training data in practice often arrive at clients in a streaming fashion without ground-truth labels. Given the expensive annotation cost, it is critical to identify a subset of informative samples for labeling on clients. However, selecting samples locally while accommodating the global training objective presents a challenge unique to FL. In this work, we tackle this conundrum by framing the data querying process in FL as a collaborative decentralized decision-making problem and proposing an effective solution named LeaDQ, which leverages multi-agent reinforcement learning algorithms. In particular, under the implicit guidance from global information, LeaDQ effectively learns the local policies for distributed clients and steers them towards selecting samples that can enhance the global model's accuracy. Extensive simulations on image and text tasks show that LeaDQ advances the model performance in various FL scenarios, outperforming the benchmarking algorithms.

Describing skills in natural language has the potential to provide an accessible way to inject human knowledge about decision-making into an AI system. We present MaestroMotif, a method for AI-assisted skill design, which yields high-performing and adaptable agents. MaestroMotif leverages the capabilities of Large Language Models (LLMs) to effectively create and reuse skills. It first uses an LLM's feedback to automatically design rewards corresponding to each skill, starting from their natural language description. Then, it employs an LLM's code generation abilities, together with reinforcement learning, for training the skills and combining them to implement complex behaviors specified in language. We evaluate MaestroMotif using a suite of complex tasks in the NetHack Learning Environment (NLE), demonstrating that it surpasses existing approaches in both performance and usability.

Reinforcement learning solves optimal control and sequential decision problems widely found in control systems engineering, robotics, and artificial intelligence. This work investigates optimal control over a sequence of natural images. The problem is formalized, and general conditions are derived for an image to be sufficient for implementing an optimal policy. Reinforcement learning is shown to be efficient only for certain types of image representations. This is demonstrated by developing a reinforcement learning benchmark that scales easily with number of states and length of horizon, and has optimal policies that are easily distinguished from suboptimal policies. Image representations given by overcomplete sparse codes are found to be computationally efficient for optimal control, using fewer computational resources to learn and evaluate optimal policies. For natural images of fixed size, representing each image as an overcomplete sparse code in a linear network is shown to increase network storage capacity by orders of magnitude beyond that possible for any complete code, allowing larger tasks with many more states to be solved. Sparse codes can be generated by devices with low energy requirements and low computational overhead.