Research map / Probabilistic and scientific modeling / Dynamical systems
Probabilistic inverse optimal control for non-linear partially observable systems disentangles perceptual uncertainty and behavioral costs
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use probabilistic IOC with explicit belief tracking instead of the MCE baseline | IOC parameter estimation · Manual reaching | median absolute relative error: 0.93 -> 0.11 | Helped |
| Use probabilistic IOC with explicit belief tracking instead of the MCE baseline | IOC parameter estimation · Navigation | median absolute relative error: 1.99 -> 0.31 | Helped |
| Use probabilistic IOC with explicit belief tracking instead of the MCE baseline | IOC parameter estimation · Pendulum | median absolute relative error: 2.21 -> 0.12 | Helped |
| Use probabilistic IOC with explicit belief tracking instead of the MCE baseline | IOC parameter estimation · Cart Pole | median absolute relative error: 3.82 -> 0.41 | Helped |
| Differentiate through the unrolled forward-control loop instead of using data-based linearization (ablation) | Probabilistic IOC on partially observable reaching · Manual reaching | parameter estimation accuracy | Hurt |
| Use last-iteration differentiation or implicit differentiation instead of data-based linearization (ablation) | Probabilistic IOC on partially observable reaching · Manual reaching | parameter estimation accuracy | No clear effect |
Closest papers by meaning
- Stochastic Optimal Control and Estimation with Multiplicative and Internal Noise (NeurIPS 2024 · similarity 0.90)
- Inverse decision-making using neural amortized Bayesian actors (ICLR 2025 · similarity 0.88)
- Causal Imitation for Markov Decision Processes: a Partial Identification Approach (NeurIPS 2024 · similarity 0.85)
- Provable Partially Observable Reinforcement Learning with Privileged Information (NeurIPS 2024 · similarity 0.85)
- How to Explore with Belief: State Entropy Maximization in POMDPs (ICML 2024 · similarity 0.84)
- World Models as Reference Trajectories for Rapid Motor Adaptation (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.