{"data":{"id":"7d6197e5-0de8-4771-b985-56b0a39c67f6","title":"The Most Overestimated Q Value Regularization in High-Dimensional Discrete Action Spaces for Offline Reinforcement Learning","summary":"Researchers propose most overestimated Q value regularization (MQR), an offline reinforcement learning algorithm for high-dimensional discrete action spaces. MQR penalizes the action with the most overestimated Q value rather than applying uniform penalties across the whole action space. On a robotic pushing and grasping task, it reached a 96.94% clearance rate in simulation and 99.04% in real-world dense configurations, and the code is publicly available.","solution":"N/A -- no mitigation discussed in source.","labels":["research"],"sourceUrl":"http://ieeexplore.ieee.org/document/11304592","publishedAt":"2025-12-19T13:19:26.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2025-12-19T13:19:26.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":null,"llmSpecific":false,"classifierConfidence":0.6,"researchCategory":"peer_reviewed","atlasIds":null}}