DoubleCheckYourStateBeforeTrustingIt: Confidence-AwareBidirectionalOfflineModel-Based Imagination
–Neural Information Processing Systems
OfflineRLisdeemed to be promising [16, 14] as online learning requires the agent to continuously interact with the environment, which howevermaybecostly,time-consuming, orevendangerous.
Neural Information Processing Systems
Feb-12-2026, 23:03:25 GMT