Recent advancements in artificial intelligence (AI) applications within aerospace have demonstrated substantial growth, particularly in the context of control systems. As High Performance Computing (HPC) platforms continue to evolve, they are expected to replace current flight control or engine control computers, enabling increased computational capabilities. This shift will allow real-time AI applications, such as image processing and defect detection, to be seamlessly integrated into monitoring systems, providing real-time awareness and enhanced fault detection and accommodation. Furthermore, AI's potential in aerospace extends to control systems, where its application can range from full autonomy to enhancing human control through assistive features. AI, particularly deep reinforcement learning (DRL), can offer significant improvements in control systems, whether for autonomous operation or as an augmentative tool.

The nonlinear and unstable aerodynamic interference generated by the tandem wings of such biomimetic systems poses substantial challenges for motion control, especially under multiple random operating conditions. To address these challenges, the Concerto Reinforcement Learning Extension (CRL2E) algorithm has been developed. This plug-and-play, fully on-the-job, real-time reinforcement learning algorithm incorporates a novel Physics-Inspired Rule-Based Policy Composer Strategy with a Perturbation Module alongside a lightweight network optimized for real-time control. To validate the performance and the rationality of the module design, experiments were conducted under six challenging operating conditions, comparing seven different algorithms. The results demonstrate that the CRL2E algorithm achieves safe and stable training within the first 500 steps, improving tracking accuracy by 14 to 66 times compared to the Soft Actor-Critic, Proximal Policy Optimization, and Twin Delayed Deep Deterministic Policy Gradient algorithms. Additionally, CRL2E significantly enhances performance under various random operating conditions, with improvements in tracking accuracy ranging from 8.3% to 60.4% compared to the Concerto Reinforcement Learning (CRL) algorithm. The convergence speed of CRL2E is 36.11% to 57.64% faster than the CRL algorithm with only the Composer Perturbation and 43.52% to 65.85% faster than the CRL algorithm when both the Composer Perturbation and Time-Interleaved Capability Perturbation are introduced, especially in conditions where the standard CRL struggles to converge. Hardware tests indicate that the optimized lightweight network structure excels in weight loading and average inference time, meeting real-time control requirements.

Figure 1: Live-rendered frames taken from ManiSkill-HAB environments while running policy rollouts with skill chaining. High-quality benchmarks are the foundation for embodied AI research, enabling significant advancements in long-horizon navigation, manipulation and rearrangement tasks. However, as frontier tasks in robotics get more advanced, they require faster simulation speed, more intricate test environments, and larger demonstration datasets. To this end, we present MS-HAB, a holistic benchmark for lowlevel manipulation and in-home object rearrangement. First, we provide a GPUaccelerated implementation of the Home Assistant Benchmark (HAB). We support realistic low-level control and achieve over 3x the speed of previous magical grasp implementations at similar GPU memory usage. Second, we train extensive reinforcement learning (RL) and imitation learning (IL) baselines for future work to compare against. Finally, we develop a rule-based trajectory filtering system to sample specific demonstrations from our RL policies which match predefined criteria for robot behavior and safety. Combining demonstration filtering with our fast environments enables efficient, controlled data generation at scale. An important goal of embodied AI is to create robots that can solve manipulation tasks in home-scale environments. Recently, faster and more realistic simulation, home-scale rearrangement benchmarks, and large robot datasets have provided important platforms to accelerate research towards this goal. However, there remains a need for all of these features in one unified benchmark. Fast Manipulation Simulation with Realistic Physics and Rendering: Using ManiSkill3 (Tao et al., 2024), we implement a GPU-accelerated version of the HAB (Szot et al., 2021), an apartmentscale rearrangement benchmark containing three long-horizon tasks using the Fetch mobile manipulator (ZebraTechnologies, 2024). While the original HAB uses magical grasp (teleport closest object within 15cm to the gripper), we require realistic grasping.

Assignment problems are a classic combinatorial optimization problem in which a group of agents must be assigned to a group of tasks such that maximum utility is achieved while satisfying assignment constraints. Given the utility of each agent completing each task, polynomial-time algorithms exist to solve a single assignment problem in its simplest form. However, in many modern-day applications such as satellite constellations, power grids, and mobile robot scheduling, assignment problems unfold over time, with the utility for a given assignment depending heavily on the state of the system. We apply multi-agent reinforcement learning to this problem, learning the value of assignments by bootstrapping from a known polynomial-time greedy solver and then learning from further experience. We then choose assignments using a distributed optimal assignment mechanism rather than by selecting them directly. We demonstrate that this algorithm is theoretically justified and avoids pitfalls experienced by other RL algorithms in this setting. Finally, we show that our algorithm significantly outperforms other methods in the literature, even while scaling to realistic scenarios with hundreds of agents and tasks.

Dyna-style off-policy model-based reinforcement learning (DMBRL) algorithms are a family of techniques for generating synthetic state transition data and thereby enhancing the sample efficiency of off-policy RL algorithms. This paper identifies and investigates a surprising performance gap observed when applying DMBRL algorithms across different benchmark environments with proprioceptive observations. We show that, while DMBRL algorithms perform well in OpenAI Gym, their performance can drop significantly in DeepMind Control Suite (DMC), even though these settings offer similar tasks and identical physics backends. Modern techniques designed to address several key issues that arise in these settings do not provide a consistent improvement across all environments, and overall our results show that adding synthetic rollouts to the training process -- the backbone of Dyna-style algorithms -- significantly degrades performance across most DMC environments. Our findings contribute to a deeper understanding of several fundamental challenges in model-based RL and show that, like many optimization fields, there is no free lunch when evaluating performance across diverse benchmarks in RL.

Recently, a state-of-the-art family of algorithms, known as Goal-Conditioned Weighted Supervised Learning (GCWSL) methods, has been introduced to tackle challenges in offline goal-conditioned reinforcement learning (RL). GCWSL optimizes a lower bound of the goal-conditioned RL objective and has demonstrated outstanding performance across diverse goal-reaching tasks, providing a simple, effective, and stable solution. However, prior research has identified a critical limitation of GCWSL: the lack of trajectory stitching capabilities. To address this, goal data augmentation strategies have been proposed to enhance these methods. Nevertheless, existing techniques often struggle to sample suitable augmented goals for GCWSL effectively. In this paper, we establish unified principles for goal data augmentation, focusing on goal diversity, action optimality, and goal reachability. Based on these principles, we propose a Model-based Goal Data Augmentation (MGDA) approach, which leverages a learned dynamics model to sample more suitable augmented goals. MGDA uniquely incorporates the local Lipschitz continuity assumption within the learned model to mitigate the impact of compounding errors. Empirical results show that MGDA significantly enhances the performance of GCWSL methods on both state-based and vision-based maze datasets, surpassing previous goal data augmentation techniques in improving stitching capabilities.

When robots handle navigation tasks while avoiding collisions, they perform in crowded and complex environments not as good as in stable and homogeneous environments. This often results in a low success rate and poor efficiency. Therefore, we propose a novel Foresight Social-aware Reinforcement Learning (FSRL) framework for mobile robots to achieve collision-free navigation. Compared to previous learning-based methods, our approach is foresighted. It not only considers the current human-robot interaction to avoid an immediate collision, but also estimates upcoming social interactions to still keep distance in the future. Furthermore, an efficiency constraint is introduced in our approach that significantly reduces navigation time. Comparative experiments are performed to verify the effectiveness and efficiency of our proposed method under more realistic and challenging simulated environments.

Abstraction is key to scaling up reinforcement learning (RL). However, autonomously learning abstract state and action representations to enable transfer and generalization remains a challenging open problem. This paper presents a novel approach for inventing, representing, and utilizing options, which represent temporally extended behaviors, in continual RL settings. Our approach addresses streams of stochastic problems characterized by long horizons, sparse rewards, and unknown transition and reward functions. Our approach continually learns and maintains an interpretable state abstraction, and uses it to invent high-level options with abstract symbolic representations. These options meet three key desiderata: (1) composability for solving tasks effectively with lookahead planning, (2) reusability across problem instances for minimizing the need for relearning, and (3) mutual independence for reducing interference among options. Our main contributions are approaches for continually learning transferable, generalizable options with symbolic representations, and for integrating search techniques with RL to efficiently plan over these learned options to solve new problems. Empirical results demonstrate that the resulting approach effectively learns and transfers abstract knowledge across problem instances, achieving superior sample efficiency compared to state-of-the-art methods.

REST APIs have become key components of web services. However, they often contain logic flaws resulting in server side errors or security vulnerabilities. HTTP requests are used as test cases to find and mitigate such issues. Existing methods to modify requests, including those using deep learning, suffer from limited performance and precision, relying on undirected search or making limited usage of the contextual information. In this paper we propose APIRL, a fully automated deep reinforcement learning tool for testing REST APIs. A key novelty of our approach is the use of feedback from a transformer module pre-trained on JSON-structured data, akin to that used in API responses. This allows APIRL to learn the subtleties relating to test outcomes, and generalise to unseen API endpoints. We show APIRL can find significantly more bugs than the state-of-the-art in real world REST APIs while minimising the number of required test cases. We also study how reward functions, and other key design choices, affect learnt policies in a thorough ablation study.

This paper introduces state abstraction for two-player zero-sum Markov games (TZMGs), where the payoffs for the two players are determined by the state representing the environment and their respective actions, with state transitions following Markov decision processes. For example, in games like soccer, the value of actions changes according to the state of play, and thus such games should be described as Markov games. In TZMGs, as the number of states increases, computing equilibria becomes more difficult. Therefore, we consider state abstraction, which reduces the number of states by treating multiple different states as a single state. There is a substantial body of research on finding optimal policies for Markov decision processes using state abstraction. However, in the multi-player setting, the game with state abstraction may yield different equilibrium solutions from those of the ground game. To evaluate the equilibrium solutions of the game with state abstraction, we derived bounds on the duality gap, which represents the distance from the equilibrium solutions of the ground game. Finally, we demonstrate our state abstraction with Markov Soccer, compute equilibrium policies, and examine the results.