Index
A
ACKTR, math concepts 540
block diagonal matrix 540, 541
block matrix 540
Kronecker product 542
Kronecker product, properties 543
vec operator 543
action 2, 39
actions 14
action space 18, 40, 73, 74
activation function 265
about 267
exploring 267
Rectified Linear Unit (ReLU) function 269, 270
sigmoid function 268
softmax function 270, 271
tanh function 269
activation map 300
Actor Critic 431
actor critic algorithm 428, 429
actor critic class
action, selecting 441
defining 436
global network, updating 440
init method, defining 436, 437, 439
network, building 440
worker network, updating 441
actor critic method
K-FAC, applying 546, 547, 548
overview 424, 425
working 425, 426, 427
Actor Critic using Kronecker-Factored Trust Region (ACKTR) 538, 539
actor network 598, 599
Advantage 431
Advantage Actor Critic (A2C)
about 429, 430
designing...