7 papers
Reward Machines for Signal Temporal Logic
Alper Kamil Bozkurt, Shangtong Zhang, Yuichi Motai
Signal temporal logic (STL) provides a formal language for specifying real-time properties of real-valued observations, along with a quantitative robustness score for monitoring sa…
Active Offline-to-Online Reinforcement Learning
Alper Kamil Bozkurt, Shangtong Zhang, Yuichi Motai
Background: Offline reinforcement learning (RL) enables effective policies to be trained from large, previously collected datasets and subsequently improved through limited online…
Architecture-Adaptive Uncertainty Fusion for Deepfake Detection
Ritesh Sharma, Mohammad Ghasemigol, Yuichi Motai
Deepfake detection systems achieve near-perfect accuracy on benchmarks, yet forensic deployment demands reliable prediction uncertainty. Existing uncertainty quantification (UQ) me…
Uncertainty-Aware Adaptive Sensor Fusion for Autonomous Navigation
Simegnew Yihunie Alaba, Yuichi Motai
This work introduces a hybrid deep learning approach integrated with an Unscented Kalman Filter (UKF) to enhance pose estimation accuracy in Visual-Inertial Odometry (VIO) for auto…
Multi-Column RBF Neural Network Using Adaptive and Non-Adaptive Particle Swarm Optimization
Ammar Hoori, Yuichi Motai
The radial basis function neural network (RBFN) trained with a gradient descending algorithm provides an effective fully connected structure in both shallow and deep networks. The…
Adaptive Policy Selection and Fine-Tuning under Interaction Budgets for Offline-to-Online Reinforcement Learning
Alper Kamil Bozkurt, Xiaoan Xu, Shangtong Zhang +2
In offline-to-online reinforcement learning (O2O-RL), policies are first safely trained offline using previously collected datasets and then further fine-tuned for tasks via limite…