Hybrid offline-online reinforcement learning (O2O RL) promises both sample efficiency and robust exploration, but suffers from instability due to distribution shift between offline and online data. We introduce RLPD-GX, a framework that decouples policy optimization from safety enforcement: a reward-seeking learner explores freely, while a projection-based guardian guarantees rule-consistent execution and safe value backups. This design preserves the exploratory value of online interactions without collapsing to conservative policies. To further stabilize training, we propose dynamic curricula that gradually extend temporal horizons and anneal offline-online data mixing. We prove convergence via a contraction property of the guarded Bellman operator, and empirically show state-of-the-art performance on Atari-100k, achieving a normalized mean score of 3.02 (+45% over prior hybrid methods) with stronger safety and stability. Beyond Atari, ablations demonstrate consistent gains across safety-critical and long-horizon tasks, underscoring the generality of our design. Extensive and comprehensive results highlight decoupled safety enforcement as a simple yet principled route to robust O2O RL, suggesting a broader paradigm for reconciling exploration and safety in reinforcement learning. Deep reinforcement learning (DRL) has demonstrated remarkable performance in complex decision-making tasks such as strategy games and robotic control (Zhang et al., 2025d; Mnih et al., 2015; Arulkumaran et al., 2017; Li, 2018; Dulac-Arnold et al., 2021; Zhang et al., 2025b). However, its mainstream paradigms, i.e., purely online learning and purely offline learning, are constrained by sample inefficiency and out-of-distribution (OOD) generalization challenges, respectively (Fujimoto et al., 2019; Kumar et al., 2020; Gu et al., 2024b; Zhang et al., 2025h).

We consider the distributed pose-graph optimization (PGO) problem, which is fundamental in accurate trajectory estimation in multi-robot simultaneous localization and mapping (SLAM). Conventional iterative approaches linearize a highly non-convex optimization objective, requiring repeated solving of normal equations, which often converge to local minima and thus produce suboptimal estimates. We propose a scalable, outlier-robust distributed planar PGO framework using Multi-Agent Reinforcement Learning (MARL). We cast distributed PGO as a partially observable Markov game defined on local pose-graphs, where each action refines a single edge's pose estimate. A graph partitioner decomposes the global pose graph, and each robot runs a recurrent edge-conditioned Graph Neural Network (GNN) encoder with adaptive edge-gating to denoise noisy edges. Robots sequentially refine poses through a hybrid policy that utilizes prior action memory and graph embeddings. After local graph correction, a consensus scheme reconciles inter-robot disagreements to produce a globally consistent estimate. Our extensive evaluations on a comprehensive suite of synthetic and real-world datasets demonstrate that our learned MARL-based actors reduce the global objective by an average of 37.5% more than the state-of-the-art distributed PGO framework, while enhancing inference efficiency by at least 6X. We also demonstrate that actor replication allows a single learned policy to scale effortlessly to substantially larger robot teams without any retraining. Code is publicly available at https://github.com/herolab-uga/policies-over-poses.

The growing need for autonomous on-orbit services such as inspection, maintenance, and situational awareness calls for intelligent spacecraft capable of complex maneuvers around large orbital targets. Traditional control systems often fall short in adaptability, especially under model uncertainties, multi-spacecraft configurations, or dynamically evolving mission contexts. This paper introduces RL-AVIST, a Reinforcement Learning framework for Autonomous Visual Inspection of Space Targets. Leveraging the Space Robotics Bench (SRB), we simulate high-fidelity 6-DOF spacecraft dynamics and train agents using DreamerV3, a state-of-the-art model-based RL algorithm, with PPO and TD3 as model-free baselines. Our investigation focuses on 3D proximity maneuvering tasks around targets such as the Lunar Gateway and other space assets. We evaluate task performance under two complementary regimes: generalized agents trained on randomized velocity vectors, and specialized agents trained to follow fixed trajectories emulating known inspection orbits. Furthermore, we assess the robustness and generalization of policies across multiple spacecraft morphologies and mission domains. Results demonstrate that model-based RL offers promising capabilities in trajectory fidelity, and sample efficiency, paving the way for scalable, retrainable control solutions for future space operations

Reliable value estimation serves as the cornerstone of reinforcement learning (RL) by evaluating long-term returns and guiding policy improvement, significantly influencing the convergence speed and final performance. Existing works improve the reliability of value function estimation via multi-critic ensembles and distributional RL, yet the former merely combines multi point estimation without capturing distributional information, whereas the latter relies on discretization or quantile regression, limiting the expressiveness of complex value distributions. Inspired by flow matching's success in generative modeling, we propose a generative paradigm for value estimation, named FlowCritic. Departing from conventional regression for deterministic value prediction, FlowCritic leverages flow matching to model value distributions and generate samples for value estimation.

Interactive applications demand believable characters that respond naturally to dynamic environments. Traditional character animation techniques often struggle to handle arbitrary situations, leading to a growing trend of dynamically selecting motion-captured animations based on predefined features. While Motion Matching has proven effective for locomotion by aligning to target trajectories, animating environment interactions and crowd behaviors remains challenging due to the need to consider surrounding elements. Existing approaches often involve manual setup or lack the naturalism of motion capture. Furthermore, in crowd animation, body animation is frequently treated as a separate process from trajectory planning, leading to inconsistencies between body pose and root motion. To address these limitations, we present Environment-aware Motion Matching, a novel real-time system for full-body character animation that dynamically adapts to obstacles and other agents, emphasizing the bidirectional relationship between pose and trajectory. In a preprocessing step, we extract shape, pose, and trajectory features from a motion capture database. At runtime, we perform an efficient search that matches user input and current pose while penalizing collisions with a dynamic environment. Our method allows characters to naturally adjust their pose and trajectory to navigate crowded scenes.

The coordination of multiple autonomous agents in high-speed, competitive environments represents a significant engineering challenge. This paper presents CRUISE (Curriculum-Based Iterative Self-Play for Scalable Multi-Drone Racing), a reinforcement learning framework designed to solve this challenge in the demanding domain of multi-drone racing. CRUISE overcomes key scalability limitations by synergistically combining a progressive difficulty curriculum with an efficient self-play mechanism to foster robust competitive behaviors. Validated in high-fidelity simulation with realistic quadrotor dynamics, the resulting policies significantly outperform both a standard reinforcement learning baseline and a state-of-the-art game-theoretic planner. CRUISE achieves nearly double the planner's mean racing speed, maintains high success rates, and demonstrates robust scalability as agent density increases. Ablation studies confirm that the curriculum structure is the critical component for this performance leap. By providing a scalable and effective training methodology, CRUISE advances the development of autonomous systems for dynamic, competitive tasks and serves as a blueprint for future real-world deployment.

Social Robot Navigation is the skill that allows robots to move efficiently in human-populated environments while ensuring safety, comfort, and trust. Unlike other areas of research, the scientific community has not yet achieved an agreement on how Social Robot Navigation should be benchmarked. This is notably important, as the lack of a de facto standard to benchmark Social Robot Navigation can hinder the progress of the field and may lead to contradicting conclusions. Motivated by this gap, we contribute with a short review focused exclusively on benchmarking trends in the period from January 2020 to July 2025. Of the 130 papers identified by our search using IEEE Xplore, we analysed the 85 papers that met the criteria of the review. This review addresses the metrics used in the literature for benchmarking purposes, the algorithms employed in such benchmarks, the use of human surveys for benchmarking, and how conclusions are drawn from the benchmarking results, when applicable.

High-temperature superconductors are essential for next-generation energy and quantum technologies, yet their performance is often limited by the critical current density ($J_c$), which is strongly influenced by microstructural defects. Optimizing $J_c$ through defect engineering is challenging due to the complex interplay of defect type, density, and spatial correlation. Here we present an integrated workflow that combines reinforcement learning (RL) with time-dependent Ginzburg-Landau (TDGL) simulations to autonomously identify optimal defect configurations that maximize $J_c$. In our framework, TDGL simulations generate current-voltage characteristics to evaluate $J_c$, which serves as the reward signal that guides the RL agent to iteratively refine defect configurations. We find that the agent discovers optimal defect densities and correlations in two-dimensional thin-film geometries, enhancing vortex pinning and $J_c$ relative to the pristine thin-film, approaching 60\% of theoretical depairing limit with up to 15-fold enhancement compared to random initialization. This RL-driven approach provides a scalable strategy for defect engineering, with broad implications for advancing HTS applications in fusion magnets, particle accelerators, and other high-field technologies.

Controlling high-dimensional stochastic systems, critical in robotics, autonomous vehicles, and hyperchaotic systems, faces the curse of dimensionality, lacks temporal abstraction, and often fails to ensure stochastic stability. To overcome these limitations, this study introduces the Multi-Timescale Lyapunov-Constrained Hierarchical Reinforcement Learning (MTLHRL) framework. MTLHRL integrates a hierarchical policy within a semi-Markov Decision Process (SMDP), featuring a high-level policy for strategic planning and a low-level policy for reactive control, which effectively manages complex, multi-timescale decision-making and reduces dimensionality overhead. Stability is rigorously enforced using a neural Lyapunov function optimized via Lagrangian relaxation and multi-timescale actor-critic updates, ensuring mean-square boundedness or asymptotic stability in the face of stochastic dynamics. The framework promotes efficient and reliable learning through trust-region constraints and decoupled optimization. Extensive simulations on an 8D hyperchaotic system and a 5-DOF robotic manipulator demonstrate MTLHRL's empirical superiority. It significantly outperforms baseline methods in both stability and performance, recording the lowest error indices (e.g., Integral Absolute Error (IAE): 3.912 in hyperchaotic control and IAE: 1.623 in robotics), achieving faster convergence, and exhibiting superior disturbance rejection. MTLHRL offers a theoretically grounded and practically viable solution for robust control of complex stochastic systems.

In this paper, we propose Bootstrapped Language-Image Pretraining-driven Fused State Representation in Proximal Policy Optimization (BLIP-FusePPO), a novel multimodal reinforcement learning (RL) framework for autonomous lane-keeping (LK), in which semantic embeddings generated by a vision-language model (VLM) are directly fused with geometric states, LiDAR observations, and Proportional-Integral-Derivative-based (PID) control feedback within the agent observation space. The proposed method lets the agent learn driving rules that are aware of their surroundings and easy to understand by combining high-level scene understanding from the VLM with low-level control and spatial signals. Our architecture brings together semantic, geometric, and control-aware representations to make policy learning more robust. A hybrid reward function that includes semantic alignment, LK accuracy, obstacle avoidance, and speed regulation helps learning to be more efficient and generalizable. Our method is different from the approaches that only use semantic models to shape rewards. Instead, it directly embeds semantic features into the state representation. This cuts down on expensive runtime inference and makes sure that semantic guidance is always available. The simulation results show that the proposed model is better at LK stability and adaptability than the best vision-based and multimodal RL baselines in a wide range of difficult driving situations. We make our code publicly available.