Maximum Entropy Inverse Reinforcement Learning Based on Frenet Frame Sampling for Human-Like Autonomous Driving.
Tangyike ZhangShuo SunJiamin ShiShitao ChenMarcelo H. AngJingmin XinNanning ZhengPublished in: ITSC (2023)
Keyphrases
- maximum entropy
- autonomous driving
- inverse reinforcement learning
- grand challenge
- maximum entropy principle
- preference elicitation
- stereo vision
- markov models
- conditional random fields
- reward function
- random sampling
- vision algorithms
- urban traffic
- temporal difference
- monte carlo
- objective function
- learning algorithm
- vision system
- multi objective
- reinforcement learning