Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Learn-To-Race: A Multimodal Control Environment for Autonomous Racing
James Herman, Jonathan Francis, Siddha Ganju, Bingqing Chen, Anirudh Koul, Abhinav Gupta, Alexey Skabelkin, Ivan Zhukov, Max Kumskoy, Eric Nyberg
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 |
|---|---|---|---|
| evaluate on unseen Las Vegas test track instead of Thruxton training track | RL-SAC · Learn-to-Race | Episode Completion Percentage: 31.1 -> 11.8 | Hurt |
| evaluate on unseen Las Vegas test track instead of Thruxton training track | MPC · Learn-to-Race | Episode Completion Percentage: 100.0 -> 69.5 | Hurt |
| evaluate on unseen Las Vegas test track instead of Thruxton training track | RL-SAC · Learn-to-Race | Average Displacement Error: 0.5 -> 1.3 | Hurt |
| use human expert instead of MPC | Learn-to-Race Thruxton · Learn-to-Race Thruxton | Episode Duration: 904.2 -> 235.8 | Improved |
| use RL-SAC instead of MPC | Learn-to-Race Thruxton · Learn-to-Race Thruxton | Average Displacement Error: 0.9 -> 0.5 | Improved |
| use RL-SAC instead of MPC | Learn-to-Race Thruxton · Learn-to-Race Thruxton | Movement Smoothness: 10.4 -> 11.1 | Improved |
| use RL-SAC instead of MPC | Learn-to-Race Thruxton · Learn-to-Race Thruxton | Episode Completion Percentage: 100.0 -> 31.1 | Hurt |
| use human expert instead of MPC | Learn-to-Race Vegas · Learn-to-Race Vegas | Average Adjusted Track Speed: 40.5 -> 114.2 | Improved |
| use human expert instead of MPC | Learn-to-Race Vegas · Learn-to-Race Vegas | Average Displacement Error: 0.8 -> 1.7 | Hurt |
Closest papers by meaning
- A Simulation Benchmark for Autonomous Racing with Large-Scale Human Data (NeurIPS 2024 · similarity 0.89)
- SimScale: Learning to Drive via Real-World Simulation at Scale (CVPR 2026 · similarity 0.88)
- ReSim: Reliable World Simulation for Autonomous Driving (NeurIPS 2025 · similarity 0.87)
- Model-Based Imitation Learning for Urban Driving (NeurIPS 2022 · similarity 0.86)
- Knowledge Distillation from Single-Task Teachers to Multi-Task Student for End-to-End Autonomous Driving (AAAI 2024 · similarity 0.85)
- Prioritizing Perception-Guided Self-Supervision: A New Paradigm for Causal Modeling in End-to-End Autonomous Driving (NeurIPS 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.
