We introduce Reduced-Order Model-Guided Reinforcement Learning (ROM-GRL), a two-stage reinforcement learning framework for humanoid walking that requires no motion capture data or elaborate reward shaping. In the first stage, a compact 4-DOF (four-degree-of-freedom) reduced-order model (ROM) is trained via Proximal Policy Optimization. This generates energy-efficient gait templates. In the second stage, those dynamically consistent trajectories guide a full-body policy trained with Soft Actor--Critic augmented by an adversarial discriminator, ensuring the student's five-dimensional gait feature distribution matches the ROM's demonstrations. Experiments at 1 meter-per-second and 4 meter-per-second show that ROM-GRL produces stable, symmetric gaits with substantially lower tracking error than a pure-reward baseline. By distilling lightweight ROM guidance into high-dimensional policies, ROM-GRL bridges the gap between reward-only and imitation-based locomotion methods, enabling versatile, naturalistic humanoid behaviors without any human demonstrations.

Policy mirror descent (PMD) is a general policy optimization framework in reinforcement learning, which can cover a wide range of typical policy optimization methods by specifying different mirror maps. Existing analysis of PMD requires exact or approximate evaluation (for example unbiased estimation via Monte Carlo simulation) of action values solely based on policy. In this paper, we consider policy mirror descent with temporal difference evaluation (TD-PMD). It is shown that, given the access to exact policy evaluations, the dimension-free $O(1/T)$ sublinear convergence still holds for TD-PMD with any constant step size and any initialization. In order to achieve this result, new monotonicity and shift invariance arguments have been developed. The dimension free $γ$-rate linear convergence of TD-PMD is also established provided the step size is selected adaptively. For the two common instances of TD-PMD (i.e., TD-PQA and TD-NPG), it is further shown that they enjoy the convergence in the policy domain. Additionally, we investigate TD-PMD in the inexact setting and give the sample complexity for it to achieve the last iterate $\varepsilon$-optimality under a generative model, which improves the last iterate sample complexity for PMD over the dependence on $1/(1-γ)$.

The robotic assembly task poses a key challenge in building generalist robots due to the intrinsic complexity of part interactions and the sensitivity to noise perturbations in contact-rich settings. The assembly agent is typically designed in a hierarchical manner: high-level multi-part reasoning and low-level precise control. However, implementing such a hierarchical policy is challenging in practice due to the mismatch between high-level skill queries and low-level execution. To address this, we propose the Query-centric Diffusion Policy (QDP), a hierarchical framework that bridges high-level planning and low-level control by utilizing queries comprising objects, contact points, and skill information. QDP introduces a query-centric mechanism that identifies task-relevant components and uses them to guide low-level policies, leveraging point cloud observations to improve the policy's robustness. We conduct comprehensive experiments on the FurnitureBench in both simulation and real-world settings, demonstrating improved performance in skill precision and long-horizon success rate. In the challenging insertion and screwing tasks, QDP improves the skill-wise success rate by over 50% compared to baselines without structured queries.

In recent years, large language models (LLMs) have played an important role in automatic speech recognition (ASR) and text-to-speech (TTS) systems. While reinforcement learning (RL) has significantly enhanced LLM performance in text-based tasks, its application to ASR and TTS remains underexplored due to the complexity of training audio-based models. In this study, we propose a lightweight RL framework tailored for audio-based LLMs that can process audio inputs and generate audio outputs. Based on this framework, we evaluate the effectiveness of reinforcement learning on both ASR and TTS tasks. For the ASR task, we experiment with different rule-based reward functions within the Group Relative Policy Optimization (GRPO) framework and investigate the impact of RL data construction. For the TTS task, we compare GRPO with Differentiable Reward Optimization (DiffRO) and further combine the two approaches to achieve improved performance. Our experiments demonstrate that RL can significantly enhance the performance of both ASR and TTS systems, even with limited training data and a small number of optimization steps.

This paper explores how deliberate mutations of reward function in reinforcement learning can produce diversified skill variations in robotic manipulation tasks, examined with a liquid pouring use case. To this end, we developed a new reward function mutation framework that is based on applying Gaussian noise to the weights of the different terms in the reward function. Inspired by the cost-benefit tradeoff model from human motor control, we designed the reward function with the following key terms: accuracy, time, and effort. The study was performed in a simulation environment created in NVIDIA Isaac Sim, and the setup included Franka Emika Panda robotic arm holding a glass with a liquid that needed to be poured into a container. The reinforcement learning algorithm was based on Proximal Policy Optimization. We systematically explored how different configurations of mutated weights in the rewards function would affect the learned policy. The resulting policies exhibit a wide range of behaviours: from variations in execution of the originally intended pouring task to novel skills useful for unexpected tasks, such as container rim cleaning, liquid mixing, and watering. This approach offers promising directions for robotic systems to perform diversified learning of specific tasks, while also potentially deriving meaningful skills for future tasks.

Utilizing offline reinforcement learning (RL) with real-world clinical data is getting increasing attention in AI for healthcare. However, implementation poses significant challenges. Defining direct rewards is difficult, and inverse RL (IRL) struggles to infer accurate reward functions from expert behavior in complex environments. Offline RL also encounters challenges in aligning learned policies with observed human behavior in healthcare applications. To address challenges in applying offline RL to physical activity promotion for older adults at high risk of falls, based on wearable sensor activity monitoring, we introduce Kolmogorov-Arnold Networks and Diffusion Policies for Offline Inverse Reinforcement Learning (KANDI). By leveraging the flexible function approximation in Kolmogorov-Arnold Networks, we estimate reward functions by learning free-living environment behavior from low-fall-risk older adults (experts), while diffusion-based policies within an Actor-Critic framework provide a generative approach for action refinement and efficiency in offline RL. We evaluate KANDI using wearable activity monitoring data in a two-arm clinical trial from our Physio-feedback Exercise Program (PEER) study, emphasizing its practical application in a fall-risk intervention program to promote physical activity among older adults. Additionally, KANDI outperforms state-of-the-art methods on the D4RL benchmark. These results underscore KANDI's potential to address key challenges in offline RL for healthcare applications, offering an effective solution for activity promotion intervention strategies in healthcare.

Diffusion large language models (dLLMs) have emerged as a new architecture following auto regressive models. Their denoising process offers a powerful generative advantage, but they present significant challenges in learning and understanding numerically sensitive mathematical and order-sensitive logical tasks. Current training methods, including pre-training, fine-tuning, and reinforcement learning, focus primarily on improving general knowledge retention and reasoning abilities, but lack a comprehensive understanding of mathematical and logical patterns. We propose DSFT, a simple yet effective Diffusion SFT strategy, by adjusting the masking strategy and loss function, guiding models to understand mathematical and logical patterns. This strategy can be flexibly combined with pre-training, reinforcement learning, and other training methods. Validated on models such as LLaDA and Dream series, we prove that DSFT on small-scale data can achieve improvements of 5-10% and approximately 2% on mathematical and logical problems, respectively. This inspiring masking approach offers insights for future learning of specific patterns, which can be easily and efficiently combined with other training methods and applied to various dLLMs. Our code is publicly available at https://anonymous.4open.science/r/DSFT-0FFB/

Healthcare systems face increasing pressure to allocate limited nursing resources efficiently while accounting for skill heterogeneity, patient acuity, staff fatigue, and continuity of care. Traditional optimization and heuristic scheduling methods struggle to capture these dynamic, multi-constraint environments. I propose NurseSchedRL, a reinforcement learning framework for nurse-patient assignment that integrates structured state encoding, constrained action masking, and attention-based representations of skills, fatigue, and geographical context. NurseSchedRL uses Proximal Policy Optimization (PPO) with feasibility masks to ensure assignments respect real-world constraints, while dynamically adapting to patient arrivals and varying nurse availability. In simulation with realistic nurse and patient data, NurseSchedRL achieves improved scheduling efficiency, better alignment of skills to patient needs, and reduced fatigue compared to baseline heuristic and unconstrained RL approaches. These results highlight the potential of reinforcement learning for decision support in complex, high-stakes healthcare workforce management.

Recent advances have significantly improved our understanding of the sample complexity of learning in average-reward Markov decision processes (AMDPs) under the generative model. However, much less is known about the constrained average-reward MDP (CAMDP), where policies must satisfy long-run average constraints. In this work, we address this gap by studying the sample complexity of learning an $ε$-optimal policy in CAMDPs under a generative model. We propose a model-based algorithm that operates under two settings: (i) relaxed feasibility, which allows small constraint violations, and (ii) strict feasibility, where the output policy satisfies the constraint. We show that our algorithm achieves sample complexities of $\tilde{O}\left(\frac{S A (B+H)}{ ε^2}\right)$ and $\tilde{O} \left(\frac{S A (B+H)}{ε^2 ζ^2} \right)$ under the relaxed and strict feasibility settings, respectively. Here, $ζ$ is the Slater constant indicating the size of the feasible region, $H$ is the span bound of the bias function, and $B$ is the transient time bound. Moreover, a matching lower bound of $\tildeΩ\left(\frac{S A (B+H)}{ ε^2ζ^2}\right)$ for the strict feasibility case is established, thus providing the first minimax-optimal bounds for CAMDPs. Our results close the theoretical gap in understanding the complexity of constrained average-reward MDPs.

The ability of social robots to respond to human emotions is crucial for building trust and acceptance in human-robot collaborative environments. However, developing such capabilities through online reinforcement learning is sometimes impractical due to the prohibitive cost of data collection and the risk of generating unsafe behaviors. In this paper, we study the use of offline reinforcement learning as a practical and efficient alternative. This technique uses pre-collected data to enable emotion-adaptive social robots. We present a system architecture that integrates multimodal sensing and recognition, decision-making, and adaptive responses. Using a limited dataset from a human-robot game-playing scenario, we establish a benchmark for comparing offline reinforcement learning algorithms that do not require an online environment. Our results show that BCQ and CQL are more robust to data sparsity, achieving higher state-action values compared to NFQ, DQN, and DDQN. This work establishes a foundation for benchmarking offline RL in emotion-adaptive robotics and informs future deployment in real-world HRI. Our findings provide empirical insight into the performance of offline reinforcement learning algorithms in data-constrained HRI. This work establishes a foundation for benchmarking offline RL in emotion-adaptive robotics and informs its future deployment in real-world HRI, such as in conversational agents, educational partners, and personal assistants, require reliable emotional responsiveness.