Errata

Learning Ray

Errata for Learning Ray

Submit your own errata for this product.

The errata list is a list of errors and their corrections that were found after the product was released.

The following errata were submitted by our customers and have not yet been approved or disproved by the author or editor. They solely represent the opinion of the customer.

Color Key: Serious technical mistake Minor technical mistake Language or formatting error Typo Question Note Update

Version Location Description Submitted by Date submitted
PDF Page page 74, section "Running the RLlib CLI"
the command line (rllib evaluate ...)

In the "rllib evaluate" command example we should be using "maze_gym_env.GymEnvironment" instead of "maze_gym_env.Environment" as a --env parameter value.
As, like the next paragraph says:
"The algorithm used in --algo and the environment specified with --env have to match the ones used in the training run" :)
Because maze.py uses "maze_gym_env.GymEnvironment" for training.

The book is great though, love it!

 Vladyslav Bachurin  Jun 19, 2023 
PDF Page page 76, section "Training RLlib algorithms"
2nd paragraph, starting with "From printing the config dictionary..."

1. The code doesn't actually print the configuration, because `pretty_print(config.to_dict())` is not wrapped into the `print()` call.
2. "From printing the config dictionary, you can verify that the num_rollout_workers parameter is set to 2." From what I can see, there's no `num_rollout_workers` parameter in the config. Only `num_workers` and `num_healthy_workers`.

Vladyslav Bachurin  Jun 19, 2023 
Printed, PDF Page 89
first code section

The following code line was repeated twice. We only need it once.

grid[self.agents[2][0]][self.agents[2][1]] = '|2'

 Zheng Shao  Sep 06, 2023 
Printed Page 109
2nd paragraph

“minimize or optimize” should be “minimize or maximize”

 Zheng Shao  Sep 07, 2023 
Printed Page 138
Figure 6-6

Horvod should be Horovod

 Zheng Shao  Sep 07, 2023