Recent advances in audio-based generative language models have accelerated AI-driven lyric-to-song generation. However, these models frequently suffer from content hallucination, producing outputs misaligned with the input lyrics and undermining musical coherence. Current supervised fine-tuning (SFT) approaches, limited by passive label-fitting, exhibit constrained self-improvement and poor hallucination mitigation. To address this core challenge, we propose a novel reinforcement learning (RL) framework leveraging preference optimization for hallucination control. Our key contributions include: (1) Developing a robust hallucination preference dataset constructed via phoneme error rate (PER) computation and rule-based filtering to capture alignment with human expectations; (2) Implementing and evaluating three distinct preference optimization strategies within the RL framework: Direct Preference Optimization (DPO), Proximal Policy Optimization (PPO), and Group Relative Policy Optimization (GRPO). DPO operates off-policy to enhance positive token likelihood, achieving a significant 7.4% PER reduction. PPO and GRPO employ an on-policy approach, training a PER-based reward model to iteratively optimize sequences via reward maximization and KL-regularization, yielding PER reductions of 4.9% and 4.7%, respectively. Comprehensive objective and subjective evaluations confirm that our methods effectively suppress hallucinations while preserving musical quality. Crucially, this work presents a systematic, RL-based solution to hallucination control in lyric-to-song generation. The framework's transferability also unlocks potential for music style adherence and musicality enhancement, opening new avenues for future generative song research.

Maze navigation is a fundamental challenge in robotics, requiring agents to traverse complex environments efficiently. While the Deep Deterministic Policy Gradient (DDPG) algorithm excels in control tasks, its performance in maze navigation suffers from sparse rewards, inefficient exploration, and long-horizon planning difficulties, often leading to low success rates and average rewards, sometimes even failing to achieve effective navigation. To address these limitations, this paper proposes an efficient Hierarchical DDPG (HDDPG) algorithm, which includes high-level and low-level policies. The high-level policy employs an advanced DDPG framework to generate intermediate subgoals from a long-term perspective and on a higher temporal scale. The low-level policy, also powered by the improved DDPG algorithm, generates primitive actions by observing current states and following the subgoal assigned by the high-level policy. The proposed method enhances stability with off-policy correction, refining subgoal assignments by relabeling historical experiences. Additionally, adaptive parameter space noise is utilized to improve exploration, and a reshaped intrinsic-extrinsic reward function is employed to boost learning efficiency. Further optimizations, including gradient clipping and Xavier initialization, are employed to improve robustness. The proposed algorithm is rigorously evaluated through numerical simulation experiments executed using the Robot Operating System (ROS) and Gazebo. Regarding the three distinct final targets in autonomous maze navigation tasks, HDDPG significantly overcomes the limitations of standard DDPG and its variants, improving the success rate by at least 56.59% and boosting the average reward by a minimum of 519.03 compared to baseline algorithms. Keywords: Hierarchical Deep Reinforcement Learning; Deep Deterministic Policy Gradient; Off-policy Correction; Adaptive Parameter Space Noise; Reshaping Reward Function; Autonomous Maze Navigation1. Introduction In recent years, autonomous navigation for mobile robots has emerged as a pivotal research focus, driven by its potential to enhance efficiency and safety across diverse applications, which mainly strive to enable mobile robots to reach the target point while effectively avoiding obstacles [1, 2]. Maze navigation, as one of the diverse autonomous navigation tasks, poses distinct challenges. This problem is particularly relevant in critical scenarios such as warehouse logistics, search and rescue operations in disaster-stricken areas, and autonomous exploration of hazardous or unknown environments, where precise and adaptive path planning is crucial for success.

Graph Neural Networks (GNNs) have emerged as a powerful, data-driven approach for Quantum Error Correction (QEC) decoding, capable of learning complex noise characteristics directly from syndrome data. However, the robustness of these decoders against subtle, adversarial perturbations remains a critical open question. This work introduces a novel framework to systematically probe the vulnerabilities of a GNN decoder using a reinforcement learning (RL) agent. The RL agent is trained as an adversary with the goal of finding minimal syndrome modifications that cause the decoder to misclassify. We apply this framework to a Graph Attention Network (GAT) decoder trained on experimental surface code data from Google Quantum AI. Our results show that the RL agent can successfully identify specific, critical vulnerabilities, achieving a high attack success rate with a minimal number of bit flips. Furthermore, we demonstrate that the decoder's robustness can be significantly enhanced through adversarial training, where the model is retrained on the adversarial examples generated by the RL agent. This iterative process of automated vulnerability discovery and targeted retraining presents a promising methodology for developing more reliable and robust neural network decoders for fault-tolerant quantum computing.

Group Relative Policy Optimization (GRPO), recently proposed by DeepSeek, is a critic-free reinforcement learning algorithm for fine tuning large language models. It replaces the value function in Proximal Policy Optimization (PPO) with group normalized rewards, while retaining PPO style token level importance sampling based on an old policy. We show that GRPO update rule in fact estimates the policy gradient at the old policy rather than the current one. However, since the old policy is refreshed every few steps, the discrepancy between the two remains small limiting the impact of this bias in practice. We validate this through an ablation study in which importance sampling is entirely removed, and updates are instead performed using the gradient estimated at a fixed old policy across multiple optimization steps. Remarkably, this simplification results in performance comparable to standard GRPO. Motivated by these findings, we propose a new algorithm: Trajectory level Importance Corrected GRPO (TIC GRPO). TIC GRPO replaces token level importance ratios with a single trajectory level probability ratio, yielding an unbiased estimate of the current policy gradient while preserving the critic free structure. Furthermore, we present the first theoretical convergence analysis for GRPO style methods, covering both the original GRPO and our proposed variant.

Active Feature Acquisition is an instance-wise, sequential decision making problem. The aim is to dynamically select which feature to measure based on current observations, independently for each test instance. Common approaches either use Reinforcement Learning, which experiences training difficulties, or greedily maximize the conditional mutual information of the label and unobserved features, which makes myopic acquisitions. To address these shortcomings, we introduce a latent variable model, trained in a supervised manner. Acquisitions are made by reasoning about the features across many possible unobserved realizations in a stochastic latent space. Extensive evaluation on a large range of synthetic and real datasets demonstrates that our approach reliably outperforms a diverse set of baselines.

We propose an epoch-based reinforcement learning algorithm for infinite-horizon average-cost Markov decision processes (MDPs) that leverages a partial order over a policy class. In this structure, $π' \leq π$ if data collected under $π$ can be used to estimate the performance of $π'$, enabling counterfactual inference without additional environment interaction. Leveraging this partial order, we show that our algorithm achieves a regret bound of $O(\sqrt{w \log(|Θ|) T})$, where $w$ is the width of the partial order. Notably, the bound is independent of the state and action space sizes. We illustrate the applicability of these partial orders in many domains in operations research, including inventory control and queuing systems. For each, we apply our framework to that problem, yielding new theoretical guarantees and strong empirical results without imposing extra assumptions such as convexity in the inventory model or specialized arrival-rate structure in the queuing model.

Sequential decision-making systems routinely operate with missing or incomplete data. Classical reinforcement learning theory, which is commonly used to solve sequential decision problems, assumes Markovian observability, which may not hold under partial observability. Causal inference paradigms formalise ignorability of missingness. We show these views can be unified and generalized in order to guarantee Q-learning convergence even when the Markov property fails. To do so, we introduce the concept of relative ignorability. Relative ignorability is a graphical-causal criterion which refines the requirements for accurate decision-making based on incomplete data. Theoretical results and simulations both reveal that non-Markovian stochastic processes whose missingness is relatively ignorable with respect to causal estimands can still be optimized using standard Reinforcement Learning algorithms. These results expand the theoretical foundations of safe, data-efficient AI to real-world environments where complete information is unattainable.

Hyperparameter tuning in 3D Gaussian Splatting (3DGS) is a labor-intensive and expert-driven process, often resulting in inconsistent reconstructions and suboptimal results. We propose RLGS, a plug-and-play reinforcement learning framework for adaptive hyperparameter tuning in 3DGS through lightweight policy modules, dynamically adjusting critical hyperparameters such as learning rates and densification thresholds. The framework is model-agnostic and seam-lessly integrates into existing 3DGS pipelines without architectural modifications. We demonstrate its generalization ability across multiple state-of-the-art 3DGS variants, including Taming-3DGS and 3DGS-MCMC, and validate its robustness across diverse datasets. RLGS consistently enhances rendering quality. For example, it improves Taming-3DGS by 0.7dB PSNR on the Tanks and Temple (TNT) dataset, under a fixed Gaussian budget, and continues to yield gains even when baseline performance saturates. Our results suggest that RLGS provides an effective and general solution for automating hyperparameter tuning in 3DGS training, bridging a gap in applying reinforcement learning to 3DGS.

Managing physiological variables within clinically safe target zones is a central challenge in healthcare, particularly for chronic conditions such as Type 1 Diabetes Mellitus (T1DM). Reinforcement learning (RL) offers promise for personalising treatment, but struggles with the delayed and heterogeneous effects of interventions. We propose a novel RL framework to study and support decision-making in T1DM technologies, such as automated insulin delivery. Our approach captures the complex temporal dynamics of treatment by unifying two control modalities: \textit{impulse control} for discrete, fast-acting interventions (e.g., insulin boluses), and \textit{switching control} for longer-acting treatments and regime shifts. The core of our method is a constrained Markov decision process augmented with physiological state features, enabling safe policy learning under clinical and resource constraints. The framework incorporates biologically realistic factors, including insulin decay, leading to policies that better reflect real-world therapeutic behaviour. While not intended for clinical deployment, this work establishes a foundation for future safe and temporally-aware RL in healthcare. We provide theoretical guarantees of convergence and demonstrate empirical improvements in a stylised T1DM control task, reducing blood glucose level violations from 22.4\% (state-of-the-art) to as low as 10.8\%.

Safe Reinforcement Learning (RL) often faces significant issues such as constraint violations and instability, necessitating the use of constrained policy optimization, which seeks optimal policies while ensuring adherence to specific constraints like safety. Typically, constrained optimization problems are addressed by the Lagrangian method, a post-violation remedial approach that may result in oscillations and overshoots. Motivated by this, we propose a novel method named Proactive Constrained Policy Optimization (PCPO) that incorporates a preemptive penalty mechanism. This mechanism integrates barrier items into the objective function as the policy nears the boundary, imposing a cost. Meanwhile, we introduce a constraint-aware intrinsic reward to guide boundary-aware exploration, which is activated only when the policy approaches the constraint boundary. We establish theoretical upper and lower bounds for the duality gap and the performance of the PCPO update, shedding light on the method's convergence characteristics. Additionally, to enhance the optimization performance, we adopt a policy iteration approach. An interesting finding is that PCPO demonstrates significant stability in experiments. Experimental results indicate that the PCPO framework provides a robust solution for policy optimization under constraints, with important implications for future research and practical applications.