Pseudo-expert regularized offline RL reduces collisions and improves route completion for camera-based driving models trained on fixed simulator datasets from nuScenes.
Think2drive: Efficient reinforcement learning by thinking with latent world model for autonomous driving (in carla- v2)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pseudo-Expert Regularized Offline RL for End-to-End Autonomous Driving in Photorealistic Closed-Loop Environments
Pseudo-expert regularized offline RL reduces collisions and improves route completion for camera-based driving models trained on fixed simulator datasets from nuScenes.