World-model-based reinforcement learning achieves high sample efficiency by learning from imagined rollouts. However, its success critically depends on the accuracy of the learned world model, which is prone to producing unrealistic or hallucinated rollouts when queried beyond its domain of competence. These flawed predictions can trap the agent in a vicious cycle: by misleading exploration toward implausible or uninformative regions, they degrade the quality of collected data, which in turn corrupts policy learning with inaccurate rollouts. To break this cycle, we introduce the notion of a knowledge boundary—the region within which the world model provides reliable predictions—and propose a unified framework that both identifies and leverages this boundary. Concretely, we approximate the boundary using model uncertainty, quantified via disagreement across an ensemble of lightweight predictors, which serves as a practical proxy. This uncertainty signal is used in two complementary ways: as an intrinsic reward to guide exploration toward under-explored yet learnable regions, and as a dynamic filter to exclude unreliable imagined rollouts from policy optimization. Extensive experiments across diverse benchmarks—including CARLA, DeepMind Control Suite, Atari, and MemoryMaze—demonstrate that our approach consistently outperforms prior state-of-the-art methods.

Visual reinforcement learning (RL) suffers from poor sample efficiency due to high-dimensional observations in complex tasks. While existing works have shown that vision-language models (VLMs) can assist RL, they often focus on knowledge distillation from the VLM to RL, overlooking the potential of RL-generated interaction data to enhance the VLM. To address this, we propose COVR, a collaborative optimization framework that enables the mutual enhancement of the VLM and RL policies. Specifically, COVR fine-tunes the VLM with RL-generated data to enhance the semantic reasoning ability consistent with the target task, and uses the enhanced VLM to further guide policy learning via action priors. To improve fine-tuning efficiency, we introduce two key modules: (1) an Exploration-Driven Dynamic Filter module that preserves valuable exploration samples using adaptive thresholds based on the degree of exploration, and (2) a Return-Aware Adaptive Loss Weight module that improves the stability of training by quantifying the inconsistency of sampling actions via return signals of RL. We further design a progressive fine-tuning strategy to reduce resource consumption. Extensive experiments show that COVR achieves strong performance across various challenging visual control tasks.

Learning control policy from continuous action space by visual observations is a fundamental and challenging task in reinforcement learning (RL). An essential problem is how to accurately map the high-dimensional images to the optimal actions by the policy network. Traditional decision-making modules output actions solely based on the current observation, while the distributions of optimal actions are dependent on specific tasks and cannot be known priorly, which increases the learning difficulty. To make the learning easier, we analyze the action characteristics in several control tasks, and propose Reinforcement Learning with Residual Action (ResAct) to explicitly model the adjustments of actions based on the differences between adjacent observations, rather than learning actions directly from observations. The method just redefines the output of the policy network, and doesn’t introduce any prior assumption to constrain or simplify the vanilla control problem. Extensive experiments on DeepMind Control Suite and CARLA demonstrate that the method could improve different RL baselines significantly, and achieve state-of-the-art performance.

A microservice-based system is composed of numerous independently deployed and executed microservices, among which normally exist the complex dependencies. Traditional service composition approaches usually expect the business process predefined at design time. As a result, it is difficult for the microservice-based system to quickly adapt to the frequently changing operation environments and business requirements. To address the above limitations, we propose a variability-enabling and model-driven approach to developing adaptive microservice-based systems. Our approach first models the business process with variability using VxBPMN4MS, an extension of Business Process Model and Notation (BPMN) with support for variability, then transforms the business process model to variability supported microservice composition frameworks, and finally derives business process instances at run-time according to the predefined process configuration. We have developed a platform to automate the proposed approach as much as possible, and conducted a case study to evaluate the effectiveness of the proposed approach and platform.