Offline reinforcement learning (RL) learns exclusively from static datasets, without further interaction with the environment. In practice, such datasets vary widely in quality, often mixing expert, suboptimal, and even random trajectories. The choice of algorithm therefore depends on dataset fidelity. Behavior cloning can suffice on high-quality data, whereas mixed- or low-quality data typically benefits from offline RL methods that stitch useful behavior across trajectories. Yet in the wild it is difficult to assess dataset quality a priori because the data's provenance and skill composition are unknown. We address the problem of estimating offline dataset quality without training an agent. We study a spectrum of proxies from simple cumulative rewards to learned value based estimators, and introduce the Bellman Wasserstein distance (BWD), a value aware optimal transport score that measures how dissimilar a dataset's behavioral policy is from a random reference policy. BWD is computed from a behavioral critic and a state conditional OT formulation, requiring no environment interaction or full policy optimization. Across D4RL MuJoCo tasks, BWD strongly correlates with an oracle performance score that aggregates multiple offline RL algorithms, enabling efficient prediction of how well standard agents will perform on a given dataset. Beyond prediction, integrating BWD as a regularizer during policy optimization explicitly pushes the learned policy away from random behavior and improves returns. These results indicate that value aware, distributional signals such as BWD are practical tools for triaging offline RL datasets and policy optimization.

Reinforcement learning (RL) post-training for Large Language Models (LLMs) is now scaling to large clusters and running for extended durations to enhance model reasoning performance. However, the scalability of existing RL frameworks is limited, as extreme long-tail skewness in RL trajectory generation causes severe GPU underutilization. Current asynchronous RL systems attempt to mitigate this, but they rely on global weight synchronization between the actor and all rollouts, which creates a rigid model update schedule. This global synchronization is ill-suited for the highly skewed and evolving distribution of trajectory generation latency in RL training, crippling training efficiency. Our key insight is that efficient scaling requires breaking this lockstep through trajectory-level asynchrony, which generates and consumes each trajectory independently. We propose Laminar, a scalable and robust RL post-training system built on a fully decoupled architecture. First, we replace global updates with a tier of relay workers acting as a distributed parameter service. This enables asynchronous and fine-grained weight synchronization, allowing rollouts to pull the latest weight anytime without stalling the actor's training loop. Second, a dynamic repack mechanism consolidates long-tail trajectories onto a few dedicated rollouts, maximizing generation throughput. The fully decoupled design also isolates failures, ensuring robustness for long-running jobs. Our evaluation on a 1024-GPU cluster shows that Laminar achieves up to 5.48$\times$ training throughput speedup over state-of-the-art systems, while reducing model convergence time.

Active feature acquisition (AFA) is a sequential decision-making problem where the goal is to improve model performance for test instances by adaptively selecting which features to acquire. In practice, AFA methods often learn from retrospective data with systematic missingness in the features and limited task-specific labels. Most prior work addresses acquisition for a single predetermined task, limiting scalability. To address this limitation, we formalize the meta-AFA problem, where the goal is to learn acquisition policies across various tasks. We introduce Learning-to-Measure (L2M), which consists of i) reliable uncertainty quantification over unseen tasks, and ii) an uncertainty-guided greedy feature acquisition agent that maximizes conditional mutual information. We demonstrate a sequence-modeling or autoregressive pre-training approach that underpins reliable uncertainty quantification for tasks with arbitrary missingness. L2M operates directly on datasets with retrospective missingness and performs the meta-AFA task in-context, eliminating per-task retraining. Across synthetic and real-world tabular benchmarks, L2M matches or surpasses task-specific baselines, particularly under scarce labels and high missingness. Machine learning (ML) methods typically operate under the assumption that all input features are available at inference time. However, this assumption does not hold in scenarios where acquiring certain features involves significant costs or risks, such as medical diagnostics (Erion et al., 2022). For example, acquiring imaging data or invasive biopsies may incur substantial financial costs and pose potential risks to patient safety (Callender et al., 2021).

End-to-end autonomous driving models trained solely with imitation learning (IL) often suffer from poor generalization. In contrast, reinforcement learning (RL) promotes exploration through reward maximization but faces challenges such as sample inefficiency and unstable convergence. A natural solution is to combine IL and RL. Moving beyond the conventional two-stage paradigm (IL pretraining followed by RL fine-tuning), we propose CoIRL-AD, a competitive dual-policy framework that enables IL and RL agents to interact during training. CoIRL-AD introduces a competition-based mechanism that facilitates knowledge exchange while preventing gradient conflicts. Experiments on the nuScenes dataset show an 18% reduction in collision rate compared to baselines, along with stronger generalization and improved performance on long-tail scenarios. Code is available at: https://github.com/SEU-zxj/CoIRL-AD.

The competitive and cooperative forces of natural selection have driven the evolution of intelligence for millions of years, culminating in nature's vast biodiversity and the complexity of human minds. Inspired by this process, we propose a novel multi-agent reinforcement learning framework where each agent is assigned a genotype and where reward functions are modelled after the concept of inclusive fitness. An agent's genetic material may be shared with other agents, and our inclusive reward function naturally accounts for this. We study the resulting social dynamics in two types of network games with prisoner's dilemmas and find that our results align with well-established principles from biology, such as Hamilton's rule. Furthermore, we outline how this framework can extend to more open-ended environments with spatial and temporal structure, finite resources, and evolving populations. We hypothesize the emergence of an arms race of strategies, where each new strategy is a gradual improvement over earlier adaptations of other agents, effectively producing a multi-agent autocurriculum analogous to biological evolution. In contrast to the binary team-based structures prevalent in earlier research, our gene-based reward structure introduces a spectrum of cooperation ranging from full adversity to full cooperativeness based on genetic similarity, enabling unique non team-based social dynamics. For example, one agent having a mutual cooperative relationship with two other agents, while the two other agents behave adversarially towards each other. We argue that incorporating inclusive fitness in agents provides a foundation for the emergence of more strategically advanced and socially intelligent agents.

In a Human-Robot Cooperation (HRC) environment, safety and efficiency are the two core properties to evaluate robot performance. However, safety mechanisms usually hinder task efficiency since human intervention will cause backup motions and goal failures of the robot. Frequent motion replanning will increase the computational load and the chance of failure. In this paper, we present a hybrid Reinforcement Learning (RL) planning framework which is comprised of an interactive motion planner and a RL task planner. The RL task planner attempts to choose statistically safe and efficient task sequences based on the feedback from the motion planner, while the motion planner keeps the task execution process collision-free by detecting human arm motions and deploying new paths when the previous path is not valid anymore. Intuitively, the RL agent will learn to avoid dangerous tasks, while the motion planner ensures that the chosen tasks are safe. The proposed framework is validated on the cobot in both simulation and the real world, we compare the planner with hard-coded task motion planning methods. The results show that our planning framework can 1) react to uncertain human motions at both joint and task levels; 2) reduce the times of repeating failed goal commands; 3) reduce the total number of replanning requests.

Autonomous driving decision-making at unsignalized intersections is highly challenging due to complex dynamic interactions and high conflict risks. To achieve proactive safety control, this paper proposes a deep reinforcement learning (DRL) decision-making framework integrated with a biased attention mechanism. The framework is built upon the Soft Actor-Critic (SAC) algorithm. Its core innovation lies in the use of biased attention to construct a traffic risk predictor. This predictor assesses the long-term risk of collision for a vehicle entering the intersection and transforms this risk into a dense reward signal to guide the SAC agent in making safe and efficient driving decisions. Finally, the simulation results demonstrate that the proposed method effectively improves both traffic efficiency and vehicle safety at the intersection, thereby proving the effectiveness of the intelligent decision-making framework in complex scenarios. The code of our work is available at https://github.com/hank111525/SAC-RWB.

Current macroeconomic models with agent heterogeneity can be broadly divided into two main groups. Heterogeneous-agent general equilibrium (GE) models, such as those based on Heterogeneous Agents New Keynesian (HANK) or Krusell-Smith (KS) approaches, rely on GE and 'rational expectations', somewhat unrealistic assumptions that make the models very computationally cumbersome, which in turn limits the amount of heterogeneity that can be modelled. In contrast, agent-based models (ABMs) can flexibly encompass a large number of arbitrarily heterogeneous agents, but typically require the specification of explicit behavioural rules, which can lead to a lengthy trial-and-error model-development process. To address these limitations, we introduce MARL-BC, a framework that integrates deep multi-agent reinforcement learning (MARL) with Real Business Cycle (RBC) models. We demonstrate that MARL-BC can: (1) recover textbook RBC results when using a single agent; (2) recover the results of the mean-field KS model using a large number of identical agents; and (3) effectively simulate rich heterogeneity among agents, a hard task for traditional GE approaches. Our framework can be thought of as an ABM if used with a variety of heterogeneous interacting agents, and can reproduce GE results in limit cases. As such, it is a step towards a synthesis of these often opposed modelling paradigms.

The quality of experience (QoE) delivered by video conferencing systems is significantly influenced by accurately estimating the time-varying available bandwidth between the sender and receiver. Bandwidth estimation for real-time communications remains an open challenge due to rapidly evolving network architectures, increasingly complex protocol stacks, and the difficulty of defining QoE metrics that reliably improve user experience. In this work, we propose a deployed, human-in-the-loop, data-driven framework for bandwidth estimation to address these challenges. Our approach begins with training objective QoE reward models derived from subjective user evaluations to measure audio and video quality in real-time video conferencing systems. Subsequently, we collect roughly $1$M network traces with objective QoE rewards from real-world Microsoft Teams calls to curate a bandwidth estimation training dataset. We then introduce a novel distributional offline reinforcement learning (RL) algorithm to train a neural-network-based bandwidth estimator aimed at improving QoE for users. Our real-world A/B test demonstrates that the proposed approach reduces the subjective poor call ratio by $11.41\%$ compared to the baseline bandwidth estimator. Furthermore, the proposed offline RL algorithm is benchmarked on D4RL tasks to demonstrate its generalization beyond bandwidth estimation.

Scaling neural networks has driven breakthrough advances in machine learning, yet this paradigm fails in deep reinforcement learning (DRL), where larger models often degrade performance due to unique optimization pathologies such as plasticity loss. While recent works show that dynamically adapting network topology during training can mitigate these issues, existing studies have three critical limitations: (1) applying uniform dynamic training strategies across all modules despite encoder, critic, and actor following distinct learning paradigms, (2) focusing evaluation on basic architectures without clarifying the relative importance and interaction between dynamic training and architectural improvements, and (3) lacking systematic comparison between different dynamic approaches including sparse-to-sparse, dense-to-sparse, and sparse-to-dense. Through comprehensive investigation across modules and architectures, we reveal that dynamic sparse training strategies provide module-specific benefits that complement the primary scalability foundation established by architectural improvements. We finally distill these insights into Module-Specific Training (MST), a practical framework that further exploits the benefits of architectural improvements and demonstrates substantial scalability gains across diverse RL algorithms without algorithmic modifications.