Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement Learning.
Chenjia BaiPeng LiuKaiyu LiuLingxiao WangYingnan ZhaoLei HanZhaoran WangPublished in: IEEE Trans. Neural Networks Learn. Syst. (2023)
Keyphrases
- reinforcement learning
- action selection
- state space
- image segmentation
- function approximation
- autonomous learning
- neural network
- learning algorithm
- reinforcement learning algorithms
- model based reinforcement learning
- real time
- active exploration
- exploration strategy
- interactive exploration
- optimal policy
- optical flow
- case study