Customized trainer

Can you give an example of customizing trainer? It is difficult to make large modifications via yaml file. Currently it seems that the start-kit only supports customizing envs and NN models.

Thank you.

Hello @kaixin

Did you have a look at

If you are looking for an even low-level implementation, this should be a good starting point, If you plan to follow this one, please make sure that you are able to train your agent locally with the configuration provided in FAQ: Round 1 evaluations configuration.

Thank you for your quick reply. I will look at them :smile:

@jyotish by the way, can you help look at submission #75308? I just clone and submit the impala-baseline but training failed in one of the environments.