Probabilistic Inverse Optimal Control For Non-linear Partially Observable Systems Disentangles Perceptual Uncertainty And Behavioral Costs

Abstract

Inverse optimal control can be used to characterize behavior in sequential decision-making tasks. Most existing work, however, is limited to fully observable or linear systems, or requires the action signals to be known. Here, we introduce a probabilistic approach to inverse optimal control for partially observable stochastic non-linear systems with unobserved action signals, which unifies previous approaches to inverse optimal control with maximum causal entropy formulations. Using an explicit model of the noise characteristics of the sensory and motor systems of the agent in conjunction with local linearization techniques, we derive an approximate likelihood function for the model parameters, which can be computed within a single forward pass. We present quantitative evaluations on stochastic and partially observable versions of two classic control tasks and two human behavioral tasks. Importantly, we show that our method can disentangle perceptual factors and behavioral costs despit

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keystraub2023probabilistic

Related papers

• Inverse Optimal Control Adapted To The Noise Characteristics Of The Human Sensorimotor System (2021)0.00
• Inverse Rational Control With Partially Observable Continuous Nonlinear Dynamics (2019)0.00
• Optimal Control Of Probabilistic Dynamics Models Via Mean Hamiltonian Minimization (2025)0.00
• Modeling The Effects Of Environmental And Perceptual Uncertainty Using Deterministic Reinforcement Learning Dynamics With Partial Observability (2021)9.59
• Learning To Optimize Via Wasserstein Deep Inverse Optimal Control (2018)0.00
• Uncertainty Maximization In Partially Observable Domains: A Cognitive Perspective (2021)0.00
• Follow The Clairvoyant: An Imitation Learning Approach To Optimal Control (2022)4.52
• Inverse Decision Modeling: Learning Interpretable Representations Of Behavior (2023)0.00