| Algorithm 1 DQN Algorithm |
|
Input:
Output: Optimal policy 1: Init () 2: 3: 4: while do 5: // Iterative selection of optimal value 6: 7: 8: // Update parameters 9: Go to the next state 10: end while |
| Algorithm 1 DQN Algorithm |
|
Input:
Output: Optimal policy 1: Init () 2: 3: 4: while do 5: // Iterative selection of optimal value 6: 7: 8: // Update parameters 9: Go to the next state 10: end while |