Induced Exploration on Policy Gradients by Increasing Actor Entropy Using Advantage Target Regions.
Alfonso B. LabaoCarlo R. RaquelProspero C. Naval Jr.Published in: ICONIP (2) (2018)
Keyphrases
- information theory
- mutual information
- optimal policy
- information theoretic
- action selection
- evolutionary algorithm
- image features
- input image
- image gradient
- moving target
- fuzzy entropy
- neural network
- information entropy
- asymptotically optimal
- target tracking
- salient features
- image pixels
- optical flow
- reinforcement learning
- multiscale