Closed ritheshkumar95 closed 8 years ago
This is one line in the code that you use to stack up 4 previous timesteps of the game state.
s_t1 = np.append(x_t1, s_t[:,:,1:], axis = 2)
If you notice. If the s_t array at any point is [t1,t2,t3,t4](let's say), the new s_t1 would be [t5,t2,t3,t4] and not [t2,t3,t4,t5].
Actually, the line should be,
s_t1 = np.append(s_t[:,:,1:],x_t1,axis=2)
This has been fixed in #13
This is one line in the code that you use to stack up 4 previous timesteps of the game state.
If you notice. If the s_t array at any point is [t1,t2,t3,t4](let's say), the new s_t1 would be [t5,t2,t3,t4] and not [t2,t3,t4,t5].
Actually, the line should be,