Research map / Reinforcement learning / Visual and representation RL
Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigation
Check 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 |
|---|---|---|---|
| Apply adversarial feature adaptation to synthetic-trained UNREAL | UNREAL · Matterport3D test, RoomGoal | success rate: 32.67% ± 0.73% -> 56.27% ± 2.94% | Helped |
| Jointly apply adversarial feature adaptation and policy mimic | UNREAL · Matterport3D test, RoomGoal | SPL: 27.95% ± 1.18% -> 42.25% ± 2.23% | Helped |
| Add policy mimic after feature adaptation | UNREAL · Matterport3D test, RoomGoal | success rate: 56.27% ± 2.94% -> 58.50% ± 2.96% | Helped |
| Add policy mimic after feature adaptation | A3C · Matterport3D test, RoomGoal | success rate: 34.80% ± 0.88% -> 50.00% ± 1.88% | Helped |
| Add identity loss to adversarial feature adaptation (ablation) | UNREAL with feature adaptation · Matterport3D test, RoomGoal | success rate: 48.53% ± 2.93% -> 56.27% ± 3.94% | Helped |
| Set identity loss weight to 5*e^{-6} instead of the selected weight (ablation) | UNREAL with feature adaptation · Matterport3D test, RoomGoal | success rate: 54.00% ± 2.23% -> 56.27% ± 3.94% | Hurt |
| Increase identity loss weight to 5*e^{-2} (ablation) | UNREAL with feature adaptation · Matterport3D test, RoomGoal | success rate: 56.27% ± 3.94% -> 53.07% ± 1.55% | Hurt |
| Remove policy mimic loss (ablation) | UNREAL with feature adaptation · Matterport3D test, RoomGoal | success rate: 36.00% ± 3.55% -> 58.53% ± 2.96% | Hurt |
| Set mimic loss weight to 0.2 instead of 0.1 (ablation) | UNREAL with feature adaptation · Matterport3D test, RoomGoal | success rate: 58.53% ± 2.96% -> 34.53% ± 1.95% | Hurt |
| Set mimic loss weight to 0.5 instead of 0.1 (ablation) | UNREAL with feature adaptation · Matterport3D test, RoomGoal | success rate: 58.53% ± 2.96% -> 22.80% ± 1.85% | Hurt |
Closest papers by meaning
- Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation (CVPR 2025 · similarity 0.87)
- Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL (NeurIPS 2024 · similarity 0.87)
- Learning to Navigate Efficiently and Precisely in Real Environments (CVPR 2024 · similarity 0.87)
- Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator (NeurIPS 2026 · similarity 0.87)
- Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation (CVPR 2024 · similarity 0.86)
- Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees (Abstract Reprint) (AAAI 2024 · similarity 0.86)
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.