-
Notifications
You must be signed in to change notification settings - Fork 4
[internutopia] Add doc for building benchmark #2
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
HanqingWangAI
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Please go through the typos and check the issue about the terminated condition.
|
|
||
| First of all you should define a task class for the benchmark. In the benchmark one or more instances of the task class will be created and executed in the simulator. | ||
|
|
||
| You can refer to the [How to Add Custom Task](how-to-add-task.md) tutorial to learn how to add a custom task. The core is to implement for a task the `is_done` method to determine when the task ends. For example, the task ends when the robot reaches a certain position or reaches a certain number of steps for a navigation task. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Does the user need to define the terminated condition as well when defining a task?
|
|
||
| ### 2.2 Metric | ||
|
|
||
| The metrics are used to evaluate the performance of an agent's behavior in each task execution. The core is to implement for a metric the `update` method to update the metric with the latest observation. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The core is to implement for a metric the update method to update the metric with the latest observation. -> The key is to implement an update method for each metric, allowing it to be updated with the latest observation.
|
|
||
| <img src="../../../_static/image/internutopia_runner.webp" width="80%"> | ||
|
|
||
| With benchmark specific task and metrics, the config to create env looks like: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
benchmark specific -> benchmark-specific
No description provided.