June 2018
Intermediate to advanced
546 pages
13h 30m
English
Let’s now take a look at the results.
The convergence on Yandex data for one year requires about 10M training steps, which can take a while (GTX 1080Ti trains at a speed of 230-250 steps per second). During training, we have several charts in TensorBoard showing us what’s going on.
The following are two charts, reward_100 and steps_100, with average reward (which is in percentages) and the average length of the episode for the last 100 episodes, respectively:

Figure 3: The reward plot for the feed-forward version
The charts show us two good things: