Devil is in Narrow Policy: Unleashing Exploration in Driving VLA Models
Devil is in Narrow Policy: Unleashing Exploration in Driving VLA Models explores Curious-VLA unlocks the exploratory potential of autonomous driving models by addressing the exploit-explore dilemma, achieving state-of-the-art results on the Navsim benchmark.. Commercial viability score: 8/10 in Autonomous Driving.
BUILDER'S SANDBOX
Build This Paper
Use an AI coding agent to implement this research.
OpenAI CodexAI Agent
Lightweight coding agent in your terminal.
Claude CodeAI Agent
Agentic coding tool for terminal workflows.
AntiGravity IDEScaffolding
AI agent mindset installer and workflow scaffolder.
CursorIDE
AI-first code editor built on VS Code.
VS CodeIDE
Free, open-source editor by Microsoft.
Recommended Stack
Startup Essentials
Estimated $9K - $13K over 6-10 weeks.
See exactly what it costs to build this -- with 3 comparable funded startups.
7-day free trial. Cancel anytime.
Discover the researchers behind this paper and find similar experts.
7-day free trial. Cancel anytime.
Related Papers
- Builds On ThisUniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous DrivingViability: 7.0
- Builds On ThisRL-VLA$^3$: Reinforcement Learning VLA Accelerating via Full AsynchronismViability: 5.0
- Builds On ThisScaling Sim-to-Real Reinforcement Learning for Robot VLAs with Generative 3D WorldsViability: 7.0
- Builds On ThisSelf-Correcting VLA: Online Action Refinement via Sparse World ImaginationViability: 6.0
- Builds On ThisVLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation