Research Article
Performance Optimization Mechanism of Adolescent Physical Training Based on Reinforcement Learning and Markov Model
Algorithm 1
ABR optimization algorithm.
Input: State space and action space | Output: Q-value | (1) | Initialize Q-table; | (2) | for each state, do | (3) | Compute with formula (10); | (4) | Confirm by ; | (5) | Request to download ; | (6) | Update with formula (2); | (7) | Compute with formula (3); | (8) | if, then | (9) | Update Q-value with formula (12); | (10) | else | (11) | Update Q-value with formula (13); | (12) | endfor |
|