Outline Objects using Deep Reinforcement Learning.
Zhenxin WangSayan SarcarJingxin LiuYilin ZhengXiangshi RenPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- d objects
- individual objects
- similar objects
- data objects
- optimal policy
- state space
- moving objects
- learning algorithm
- dynamic programming
- multiscale
- three dimensional
- supervised learning
- markov decision processes
- machine learning
- partial occlusion
- function approximation
- temporal difference
- data sets
- real time