Action recognition using Correlation of Temporal Difference Frame (CTDF) - an algorithmic approach.
M. PoonkodiG. VadivuPublished in: J. Ambient Intell. Humaniz. Comput. (2021)
Keyphrases
- temporal difference
- action selection
- td learning
- reinforcement learning
- function approximation
- evaluation function
- monte carlo
- temporal difference learning
- reinforcement learning algorithms
- model free
- step size
- policy evaluation
- temporal difference methods
- decision making
- supervised learning
- markov decision processes
- function approximators
- basis functions
- machine learning algorithms
- markov chain
- least squares
- data sets