Conservative Lapse-Action Planning (CLAP): a variational access-and-dwell framework for safe AI optimization. Surf the conservative-lapse field to the best safe basin and dwell there — theorem-backed, pip-installable, with differentiable PyTorch training adapters.
machine-learning pytorch regularization trajectory-optimization ai-safety model-predictive-control model-based-rl safe-reinforcement-learning latent-dynamics variational-methods
-
Updated
May 30, 2026 - Python