Litcius/Paper detail

K-mixup: Data augmentation for offline reinforcement learning using mixup in a Koopman invariant subspace

Junwoo Jang, Jungwoo Han, Jinwhan Kim

2023Expert Systems with Applications14 citationsDOI

Topics & Concepts

Reinforcement learningComputer scienceBenchmark (surveying)Invariant (physics)Subspace topologyEmbeddingNonlinear systemStability (learning theory)Artificial intelligenceMachine learningAlgorithmMathematicsGeographyGeodesyMathematical physicsQuantum mechanicsPhysicsModel Reduction and Neural NetworksReinforcement Learning in RoboticsAdaptive Dynamic Programming Control
K-mixup: Data augmentation for offline reinforcement learning using mixup in a Koopman invariant subspace | Litcius