About your code

[sgfuigh]

Hello,after studying your code, I would like to ask how to get the state representation and action distribution updates of each time step from your encapsulated environment. I can't print the expression of the intermediate state of each step.

[ingambe]

Hello,
The environment after each call to the step function return the state, reward, a boolean to indicate if the environment is done, and an empty dictionary (to follow OpenAi's convention)
The state itself is a dictionary with two entries:

• action_mask: Contain a boolean vector with legal actions
• real_obs: The observation, containing for each job, the attributes you can use to make predictions

[sgfuigh]

Yes, thank you so much! And I wonder how to get specific results for each step? How can I directly see the  return results of the environment ? 发自我的iPad

…

------------------ Original ------------------ From: Pierre TASSEL ***@***.***> Date: Wed,Jan 5,2022 6:57 PM To: prosysscience/JSSEnv ***@***.***> Cc: sgfuigh ***@***.***>, Author ***@***.***> Subject: Re: [prosysscience/JSSEnv] About your code (Issue #5) Hello, The environment after each call to the step function return the state, reward, a boolean to indicate if the environment is done, and an empty dictionary (to follow OpenAi's convention) The state itself is a dictionary with two entries: action_mask: Contain a boolean vector with legal actions real_obs: The observation, containing for each job, the attributes you can use to make predictions — Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you authored the thread.Message ID: ***@***.***>