GAIT: Generating Aesthetic Indoor Tours with Deep Reinforcement Learning.
Desai XiePing HuXin SunSören PirkJianming ZhangRadomír MechArie E. KaufmanPublished in: ICCV (2023)
Keyphrases
- reinforcement learning
- function approximation
- learning algorithm
- human gait recognition
- state space
- optimal policy
- markov decision processes
- gait analysis
- model free
- motion capture
- human movement
- indoor environments
- optimal control
- traveling salesman problem
- machine learning
- gait recognition
- temporal difference
- reward function
- outdoor environments
- transfer learning
- human gait
- human recognition
- multi agent
- aesthetically pleasing