Optimal Control Of Probabilistic Dynamics Models Via Mean Hamiltonian Minimization

Abstract

Without exact knowledge of the true system dynamics, optimal control of non-linear continuous-time systems requires careful treatment under epistemic uncertainty. In this work, we translate a probabilistic interpretation of the Pontryagin maximum principle to the challenge of optimal control with learned probabilistic dynamics models. Our framework provides a principled treatment of epistemic uncertainty by minimizing the mean Hamiltonian with respect to a posterior distribution over the system dynamics. We propose a multiple shooting numerical method that leverages mean Hamiltonian minimization and is scalable to large-scale probabilistic dynamics models, including ensemble neural ordinary differential equations. Comparisons against other baselines in online and offline model-based reinforcement learning tasks show that our probabilistic Hamiltonian approach leads to reduced trial costs in offline settings and achieves competitive performance in online scenarios. By bridging optimal c

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyleeftink2025optimal

Related papers

• Probabilistic Inverse Optimal Control For Non-linear Partially Observable Systems Disentangles Perceptual Uncertainty And Behavioral Costs (2023)0.00
• Model-based Reinforcement Learning For Control Under Time-varying Dynamics (2026)0.00
• Optimal Exploration For Model-based RL In Nonlinear Systems (2023)0.00
• Adaptive Probabilistic Trajectory Optimization Via Efficient Approximate Inference (2016)0.00
• Inverse Rational Control With Partially Observable Continuous Nonlinear Dynamics (2019)0.00
• Optimistic Active Exploration Of Dynamical Systems (2023)0.00
• Risk-sensitive Stochastic Optimal Control As Rao-blackwellized Markovian Score Climbing (2023)0.00
• An Optimal Policy For Learning Controllable Dynamics By Exploration (2025)0.00