Research map / Reinforcement learning / Visual and representation RL
Query-Efficient Imitation Learning for End-to-End Simulated Driving
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 |
|---|---|---|---|
| train with SafeDAgger instead of DAgger | primary driving policy · TORCS | avg laps and damage per lap | Helped |
| train with SafeDAgger instead of DAgger | primary driving policy · TORCS | queries to reference policy: up to 39 folds | Helped |
| use safety classifier to switch to reference policy at test | supervised policy · TORCS | avg laps | Helped |
| train with SafeDAgger instead of DAgger | primary policy · TORCS | % time switched to reference policy | Helped |
| add more supervised training data only | primary policy · TORCS | avg laps | No clear effect |
Closest papers by meaning
- DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving (NeurIPS 2025 · similarity 0.86)
- RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning (NeurIPS 2025 · similarity 0.86)
- Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2) (NeurIPS 2025 · similarity 0.86)
- Uncertainty-Guided Never-Ending Learning to Drive (CVPR 2024 · similarity 0.86)
- Prioritizing Perception-Guided Self-Supervision: A New Paradigm for Causal Modeling in End-to-End Autonomous Driving (NeurIPS 2025 · similarity 0.86)
- Efficient Active Imitation Learning with Random Network Distillation (ICLR 2025 · similarity 0.85)
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.