Research map / Reinforcement learning / Imitation learning
Model-Based Robot Imitation with Future Image Similarity
A. Wu, AJ Piergiovanni, Michael S. Ryoo
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 |
|---|---|---|---|
| add learned stochastic prior to the future image predictor (ablation) | future similarity model (linear state) · Real-world lab target approach | success rate: 59% -> 91% | Improved |
| add learned stochastic prior to the future image predictor (ablation) | future similarity model (conv state) · Real-world lab target approach | success rate: 74% -> 94% | Improved |
| add learned stochastic prior (ablation) | future similarity model · Simulated obstacle avoidance | success rate: 41% -> 63% | Improved |
| use convolutional instead of linear state representation (ablation) | stochastic model · Real-world lab target approach | success rate: 91% -> 94% | Improved |
| use convolutional instead of linear state representation (ablation) | deterministic model · Real-world lab target approach | success rate: 59% -> 74% | Improved |
| use convolutional state representation (ablation) | stochastic model · Simulation dataset image prediction | SSIM: 0.9251 -> 0.9220 | No clear effect |
| use convolutional state representation (ablation) | stochastic model · Lab dataset image prediction | SSIM: 0.7255 -> 0.7436 | Improved |
| add stochastic latent variable to image predictor (ablation) | conv state predictor · Lab dataset image prediction | SSIM: 0.7211 -> 0.7436 | Improved |
| add stochastic latent variable to image predictor (ablation) | linear state predictor · Simulation dataset image prediction | SSIM: 0.8856 -> 0.9251 | Improved |
| use stochastic instead of deterministic future similarity critic (ablation) | FutureSim · Lab trajectory similarity to expert | DTW score: 11.22 -> 5.98 | Improved |
Closest papers by meaning
- OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation (NeurIPS 2025 · similarity 0.90)
- Prediction with Action: Visual Policy Learning via Joint Denoising Process (NeurIPS 2024 · similarity 0.89)
- PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning (ICML 2025 · similarity 0.89)
- Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation (ICLR 2025 · similarity 0.89)
- Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations (ICML 2025 · similarity 0.89)
- Robust Visual Imitation Learning with Inverse Dynamics Representations (AAAI 2024 · similarity 0.89)
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.
