Exploring Temporal Differences in 3D Convolutional Neural Networks.
Gagan KanojiaSudhakar KumawatShanmuganathan RamanPublished in: CoRR (2019)
Keyphrases
- convolutional neural networks
- temporal difference
- reinforcement learning
- function approximation
- evaluation function
- convolutional network
- td learning
- monte carlo
- model free
- step size
- reinforcement learning algorithms
- supervised learning
- policy iteration
- action selection
- data mining
- policy evaluation
- cost function
- least squares
- image classification
- search space
- pattern recognition
- dynamic programming