toolbox

Homer supports custom services, and provides a template to easily add new ones.

It could be great to add some more. Before starting to work on a custom service please open an issue to describe your idea and discuss about it.

Some ide

🐛 Bug

The documentation of DQN agent (https://stable-baselines3.readthedocs.io/en/master/modules/dqn.html) specifies that log_interval parameter is "The number of timesteps before logging". However, when set to 1 (or any other value) the logging is not made at that pace but is instead made every log_interval episode (and not timesteps). In the example below this is made every 200 timesteps.

The following applies to DDPG and TD3, and possibly other models. The following libraries were installed in a virtual environment:

numpy==1.16.4
stable-baselines==2.10.0
gym==0.14.0
tensorflow==1.14.0

Episode rewards do not seem to be updated in model.learn() before callback.on_step(). Depending on which callback.locals variable is used, this means that:

• episode rewards may n

Add new function utility which is useful in tests:

const createFactoryWithConstrain =
    <Constrain>() =>
    <U extends Constrain>(value: U): U =>
        value;

Playground with use cases – tsplay.dev/Ndo6Yw

Most algorithms have the same parse_inputs(). I think we should make a unique function, perhaps that takes the algorithm name, and that should output all the inputs.Right now we have tons of redundant parse_inputs() code.