Due to dynamic variations such as changing payload, aerodynamic disturbances, and varying platforms, a robust solution for quadrotor trajectory tracking remains challenging. To address these challenges, we present a deep reinforcement learning (DRL) framework that achieves physical dynamics invariance by directly optimizing force/torque inputs, eliminating the need for traditional intermediate control layers. Our architecture integrates a temporal trajectory encoder, which processes finite-horizon reference positions/velocities, with a latent dynamics encoder trained on historical state-action pairs to model platform-specific characteristics. Additionally, we introduce scale-aware dynamics randomization parameterized by the quadrotor's arm length, enabling our approach to maintain stability across drones spanning from 30g to 2.1kg and outperform other DRL baselines by 85% in tracking accuracy. Extensive real-world validation of our approach on the Crazyflie 2.1 quadrotor, encompassing over 200 flights, demonstrates robust adaptation to wind, ground effects, and swinging payloads while achieving less than 0.05m RMSE at speeds up to 2.0 m/s. This work introduces a universal quadrotor control paradigm that compensates for dynamic discrepancies across varied conditions and scales, paving the way for more resilient aerial systems.

To learn from data collected in diverse dynamics, Imitation from Observation (IfO) methods leverage expert state trajectories based on the premise that recovering expert state distributions in other dynamics facilitates policy learning in the current one. However, Imitation Learning inherently imposes a performance upper bound of learned policies. Additionally, as the environment dynamics change, certain expert states may become inaccessible, rendering their distributions less valuable for imitation. To address this, we propose a novel framework that integrates reward maximization with IfO, employing F-distance regularized policy optimization. This framework enforces constraints on globally accessible states--those with nonzero visitation frequency across all considered dynamics--mitigating the challenge posed by inaccessible states. By instantiating F-distance in different ways, we derive two theoretical analysis and develop a practical algorithm called Accessible State Oriented Policy Regularization (ASOR). ASOR serves as a general add-on module that can be incorporated into various RL approaches, including offline RL and off-policy RL. Extensive experiments across multiple benchmarks demonstrate ASOR's effectiveness in enhancing state-of-the-art cross-domain policy transfer algorithms, significantly improving their performance.

This paper addresses query scheduling for goal-oriented semantic communication in pull-based status update systems. We consider a system where multiple sensing agents (SAs) observe a source characterized by various attributes and provide updates to multiple actuation agents (AAs), which act upon the received information to fulfill their heterogeneous goals at the endpoint. A hub serves as an intermediary, querying the SAs for updates on observed attributes and maintaining a knowledge base, which is then broadcast to the AAs. The AAs leverage the knowledge to perform their actions effectively. To quantify the semantic value of updates, we introduce a grade of effectiveness (GoE) metric. Furthermore, we integrate cumulative perspective theory (CPT) into the long-term effectiveness analysis to account for risk awareness and loss aversion in the system. Leveraging this framework, we compute effect-aware scheduling policies aimed at maximizing the expected discounted sum of CPT-based total GoE provided by the transmitted updates while complying with a given query cost constraint. To achieve this, we propose a model-based solution based on dynamic programming and model-free solutions employing state-of-the-art deep reinforcement learning (DRL) algorithms. Our findings demonstrate that effect-aware scheduling significantly enhances the effectiveness of communicated updates compared to benchmark scheduling methods, particularly in settings with stringent cost constraints where optimal query scheduling is vital for system performance and overall effectiveness.

This paper explores the application of reinforcement learning to optimize the parameters of a Type-1 Takagi-Sugeno fuzzy controller, designed to operate as an artificial pancreas for Type 1 diabetes. The primary challenge in diabetes management is the dynamic nature of blood glucose levels, which are influenced by several factors such as meal intake and timing. Traditional controllers often struggle to adapt to these changes, leading to suboptimal insulin administration. To address this issue, we employ a reinforcement learning agent tasked with adjusting 27 parameters of the Takagi-Sugeno fuzzy controller at each time step, ensuring real-time adaptability. The study's findings demonstrate that this approach significantly enhances the robustness of the controller against variations in meal size and timing, while also stabilizing glucose levels with minimal exogenous insulin. This adaptive method holds promise for improving the quality of life and health outcomes for individuals with Type 1 diabetes by providing a more responsive and precise management tool. Simulation results are given to highlight the effectiveness of the proposed approach.

Dynamic Treatment Regimes (DTRs) provide a systematic approach for making sequential treatment decisions that adapt to individual patient characteristics, particularly in clinical contexts where survival outcomes are of interest. Censoring-Aware Tree-Based Reinforcement Learning (CA-TRL) is a novel framework to address the complexities associated with censored data when estimating optimal DTRs. We explore ways to learn effective DTRs, from observational data. By enhancing traditional tree-based reinforcement learning methods with augmented inverse probability weighting (AIPW) and censoring-aware modifications, CA-TRL delivers robust and interpretable treatment strategies. We demonstrate its effectiveness through extensive simulations and real-world applications using the SANAD epilepsy dataset, where it outperformed the recently proposed ASCL method in key metrics such as restricted mean survival time (RMST) and decision-making accuracy. This work represents a step forward in advancing personalized and data-driven treatment strategies across diverse healthcare settings.

Performance and reliability analyses of autonomous vehicles (AVs) can benefit from tools that ``amplify'' small datasets to synthesize larger volumes of plausible samples of the AV's behavior. We consider a specific instance of this data synthesis problem that addresses minimizing the AV's exposure to adverse environmental conditions during travel to a fixed goal location. The environment is characterized by a threat field, which is a strictly positive scalar field with higher intensities corresponding to hazardous and unfavorable conditions for the AV. We address the problem of synthesizing datasets of minimum exposure paths that resemble a training dataset of such paths. The main contribution of this paper is an inverse reinforcement learning (IRL) model to solve this problem. We consider time-invariant (static) as well as time-varying (dynamic) threat fields. We find that the proposed IRL model provides excellent performance in synthesizing paths from initial conditions not seen in the training dataset, when the threat field is the same as that used for training. Furthermore, we evaluate model performance on unseen threat fields and find low error in that case as well. Finally, we demonstrate the model's ability to synthesize distinct datasets when trained on different datasets with distinct characteristics.

Polynomial inequality proving is fundamental to many mathematical disciplines and finds wide applications in diverse fields. Current traditional algebraic methods are based on searching for a polynomial positive definite representation over a set of basis. However, these methods are limited by truncation degree. To address this issue, this paper proposes an approach based on reinforcement learning to find a {Krivine-basis} representation for proving polynomial inequalities. Specifically, we formulate the inequality proving problem as a linear programming (LP) problem and encode it as a basis selection problem using reinforcement learning (RL), achieving a non-negative {Krivine basis}. Moreover, a fast multivariate polynomial multiplication method based on Fast Fourier Transform (FFT) is employed to enhance the efficiency of action space search. Furthermore, we have implemented a tool called {APPIRL} (Automated Proof of Polynomial Inequalities via Reinforcement Learning). Experimental evaluation on benchmark problems demonstrates the feasibility and effectiveness of our approach. In addition, {APPIRL} has been successfully applied to solve the maximum stable set problem.

The capture of flying MAVs (micro aerial vehicles) has garnered increasing research attention due to its intriguing challenges and promising applications. Despite recent advancements, a key limitation of existing work is that capture strategies are often relatively simple and constrained by platform performance. This paper addresses control strategies capable of capturing high-maneuverability targets. The unique challenge of achieving target capture under unstable conditions distinguishes this task from traditional pursuit-evasion and guidance problems. In this study, we transition from larger MAV platforms to a specially designed, compact capture MAV equipped with a custom launching device while maintaining high maneuverability. We explore both time-optimal planning (TOP) and reinforcement learning (RL) methods. Simulations demonstrate that TOP offers highly maneuverable and shorter trajectories, while RL excels in real-time adaptability and stability. Moreover, the RL method has been tested in real-world scenarios, successfully achieving target capture even in unstable states.

Vision-Language Models (VLMs) have recently shown promising advancements in sequential decision-making tasks through task-specific fine-tuning. However, common fine-tuning methods, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) techniques like Proximal Policy Optimization (PPO), present notable limitations: SFT assumes Independent and Identically Distributed (IID) data, while PPO focuses on maximizing cumulative rewards. These limitations often restrict solution diversity and hinder generalization in multi-step reasoning tasks. To address these challenges, we introduce a novel framework, GFlowVLM, a framework that fine-tune VLMs using Generative Flow Networks (GFlowNets) to promote generation of diverse solutions for complex reasoning tasks. GFlowVLM models the environment as a non-Markovian decision process, allowing it to capture long-term dependencies essential for real-world applications. It takes observations and task descriptions as inputs to prompt chain-of-thought (CoT) reasoning which subsequently guides action selection. We use task based rewards to fine-tune VLM with GFlowNets. This approach enables VLMs to outperform prior fine-tuning methods, including SFT and RL. Empirical results demonstrate the effectiveness of GFlowVLM on complex tasks such as card games (NumberLine, BlackJack) and embodied planning tasks (ALFWorld), showing enhanced training efficiency, solution diversity, and stronger generalization capabilities across both in-distribution and out-of-distribution scenarios.

Continual Reinforcement Learning (CRL) is essential for developing agents that can learn, adapt, and accumulate knowledge over time. However, a fundamental challenge persists as agents must strike a delicate balance between plasticity, which enables rapid skill acquisition, and stability, which ensures long-term knowledge retention while preventing catastrophic forgetting. In this paper, we introduce SSDE, a novel structure-based approach that enhances plasticity through a fine-grained allocation strategy with Structured Sparsity and Dormant-guided Exploration. SSDE decomposes the parameter space into forward-transfer (frozen) parameters and task-specific (trainable) parameters. Crucially, these parameters are allocated by an efficient co-allocation scheme under sparse coding, ensuring sufficient trainable capacity for new tasks while promoting efficient forward transfer through frozen parameters. However, structure-based methods often suffer from rigidity due to the accumulation of non-trainable parameters, limiting exploration and adaptability. To address this, we further introduce a sensitivity-guided neuron reactivation mechanism that systematically identifies and resets dormant neurons, which exhibit minimal influence in the sparse policy network during inference. This approach effectively enhance exploration while preserving structural efficiency. Extensive experiments on the CW10-v1 Continual World benchmark demonstrate that SSDE achieves state-of-the-art performance, reaching a success rate of 95%, surpassing prior methods significantly in both plasticity and stability trade-offs (code is available at: https://github.com/chengqiArchy/SSDE).