BiPR-RL: Portrait relighting via bi-directional consistent deep reinforcement learning.
Yukai SongGuangxin XuXiaoyan ZhangZhijun ZhangPublished in: Comput. Vis. Image Underst. (2024)
Keyphrases
- bi directional
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- model free
- state space
- markov decision processes
- learning algorithm
- rl algorithms
- transfer learning
- temporal difference
- machine learning
- associative memory
- optimal policy
- temporal difference learning
- direct policy search
- partially observable domains
- partially observable markov decision processes
- english chinese
- actor critic
- continuous state
- control policy
- real robot
- multi agent
- lighting conditions
- policy iteration
- state action
- reinforcement learning methods
- complex domains
- autonomous learning
- artificial neural networks
- illumination conditions
- learning problems