Research map / Probabilistic and scientific modeling / Causal discovery
Causal Transfer for Imitation Learning and Decision Making under Sensor-Shift
Jalal Etesami, Philipp Geiger
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 exact linear causal transfer instead of the average-based proxy | Action-effect transfer on highD · highD | squared error | Improved |
| Use exact linear causal transfer instead of the average-based proxy | Action-effect transfer on highD · highD | variance | Hurt |
| Use the sensor-shift-aware imitation method rather than classical imitation learning | Simulated imitation learning · Simulated driving scene | policy similarity | Improved |
Closest papers by meaning
- Causal Imitation for Markov Decision Processes: a Partial Identification Approach (NeurIPS 2024 · similarity 0.91)
- Causal Imitation Learning under Expert-Observable and Expert-Unobservable Confounding (ICLR 2026 · similarity 0.90)
- Cross-domain Imitation from Observations (ICML 2021 · similarity 0.90)
- Imitation Learning from Observation with Automatic Discount Scheduling (ICLR 2024 · similarity 0.89)
- Diffusion Model-Augmented Behavioral Cloning (ICML 2024 · similarity 0.88)
- Diffusion Imitation from Observation (NeurIPS 2024 · similarity 0.88)
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.
