RDIRL is an online deep inverse reinforcement learning method that updates a learned cost after each expert demonstration with a Kalman-style second-order Newton step, and it outperforms batch IRL baselines in simulated control and radar tasks.
Extended Kalman Filtering for Recursive Online Discrete-Time Inverse Optimal Control
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We formulate the discrete-time inverse optimal control problem of inferring unknown parameters in the objective function of an optimal control problem from measurements of optimal states and controls as a nonlinear filtering problem. This formulation enables us to propose a novel extended Kalman filter (EKF) for solving inverse optimal control problems in a computationally efficient recursive online manner that requires only a single pass through the measurement data. Importantly, we show that the Jacobians required to implement our EKF can be computed efficiently by exploiting recent Pontryagin differentiable programming results, and that our consideration of an EKF enables the development of first-of-their-kind theoretical error guarantees for online inverse optimal control with noisy incomplete measurements. Our proposed EKF is shown to be significantly faster than an alternative unscented Kalman filter-based approach.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Recursive Deep Inverse Reinforcement Learning
RDIRL is an online deep inverse reinforcement learning method that updates a learned cost after each expert demonstration with a Kalman-style second-order Newton step, and it outperforms batch IRL baselines in simulated control and radar tasks.