Driving SMARTS is a regular competition designed to tackle problems caus...
When deploying Reinforcement Learning (RL) agents into a physical system...
Inverse reinforcement learning (IRL) methods assume that the expert data...
Competent multi-lane cruising requires using lane changes and within-lan...
We propose a new scheme to learn motion planning constraints from human
...
Motion planning under uncertainty is one of the main challenges in devel...
Despite the recent successes of reinforcement learning in games and robo...
We propose and demonstrate a framework called perception as prediction f...