Controlling Neural Style Transfer with Deep Reinforcement Learning.
Chengming FengJing HuXin WangShu HuBin ZhuXi WuHongtu ZhuSiwei LyuPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- transfer learning
- fitted q iteration
- network architecture
- neural network
- function approximation
- temporal difference
- state space
- model free
- cross domain
- sensory inputs
- associative memory
- bio inspired
- learning algorithm
- artificial neural
- knowledge transfer
- data sets
- neural model
- markov decision processes
- previously learned
- temporal difference learning
- biologically plausible
- optimal policy
- machine learning
- artificial neural networks
- action selection
- real robot
- deep learning
- artificial intelligence
- multi agent
- multi agent reinforcement learning
- biologically inspired
- neural fuzzy
- policy search
- learning tasks