Research map / Probabilistic and scientific modeling / Dynamical systems
InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations
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 |
|---|---|---|---|
| Add mutual-information regularization for latent codes | GAIL on unlabeled mixed driving demonstrations · TORCS pass | Accuracy | Helped |
| Add reward augmentation (ablation) | InfoGAIL driving policy · TORCS driving ablation | Average rollout distance: 1123.89 -> 1226.68 | Helped |
| Use the WGAN objective instead of the GAN objective (ablation) | InfoGAIL driving policy · TORCS driving ablation | Average rollout distance: 1177.72 -> 1226.68 | Helped |
| Add a replay buffer (ablation) | InfoGAIL driving policy · TORCS driving ablation | Average rollout distance: 1031.13 -> 1226.68 | Helped |
Closest papers by meaning
- Ess-InfoGAIL: Semi-supervised Imitation Learning from Imbalanced Demonstrations (NeurIPS 2023 · similarity 0.91)
- Latent Wasserstein Adversarial Imitation Learning (ICLR 2026 · similarity 0.91)
- Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations (NeurIPS 2025 · similarity 0.89)
- Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation (ICML 2025 · similarity 0.89)
- Diffusion Imitation from Observation (NeurIPS 2024 · similarity 0.89)
- Imitation from Observations with Trajectory-Level Generative Embeddings (NeurIPS 2026 · 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.