This repository has been archived by the owner on Aug 21, 2020. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 0
Ali test 0917 #1
Open
alnaeini
wants to merge
15
commits into
Lab41:Ali_test_0917
Choose a base branch
from
alnaeini:Ali_test_0917
base: Ali_test_0917
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Hi Ali, Could you elaborate on your updates to the environment? thanks |
@ahassanzadeh in this context of collaborative coding, please provide more details on contributions made in a PR. |
Hi Tindall ,
Sure, So my goals for this project was to tackle the approximation in tracking. I read the class in env_utils.py for position tracking and position step which used to calculate the distance of the agent from the goal. It is obviously caused some error that agent miss the goal.
So my approach was to work with unity directly. Unity has its own class for position(written in C#) which is connected to mesh collider and other component to find exact location of any object which give us exact locations without approximation.
So this PR is the raw environment that I asked Nina to run on local machine(my laptop cannot handle it) to determine the baseline cumulative reward (using tensor board). We can improve the model with hyperparameter tuning later.
That being said, I still not sure why it was needed to define the position tracking class in python. I would be appreciated to have talk in order to clarify about future approach.
Thanks,
Ali.
From: ltindall <[email protected]>
Reply-To: ltindall/animal_ai_private <[email protected]>
Date: Tuesday, October 1, 2019 at 12:28 PM
To: ltindall/animal_ai_private <[email protected]>
Cc: Ali Hassanzadsh <[email protected]>, Author <[email protected]>
Subject: Re: [ltindall/animal_ai_private] Ali test 0917 (#1)
Resent-From: Ali Hassanzadsh <[email protected]>
Hi Ali,
Could you elaborate on your updates to the environment? thanks
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub<#1>, or mute the thread<https://github.com/notifications/unsubscribe-auth/ALN4GETI5QAP6MHRN4D7E7DQMOQERANCNFSM4I4NIP4Q>.
|
ninalopatina
reviewed
Oct 9, 2019
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.
Instead of this pull request, please clone the environments repo (you can do a public clone), and put your C# code in there. Then add a README with instructions on how to run it, and submit a pull request. Please delete this branch.
Sure. I will make the new repo today. Thanks. -Ali.
From: Nina Lopatina <[email protected]>
Reply-To: ltindall/animal_ai_private <[email protected]>
Date: Tuesday, October 8, 2019 at 6:37 PM
To: ltindall/animal_ai_private <[email protected]>
Cc: Ali Hassanzadsh <[email protected]>, Mention <[email protected]>
Subject: Re: [ltindall/animal_ai_private] Ali test 0917 (#1)
@ninalopatina commented on this pull request.
Instead of this pull request, please clone the environments repo (you can do a public clone), and put your C# code in there. Then add a README with instructions on how to run it, and submit a pull request. Please delete this branch.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub<#1>, or mute the thread<https://github.com/notifications/unsubscribe-auth/ALN4GEVLWPXMI34F7XID4T3QNUYVRANCNFSM4I4NIP4Q>.
|
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hi, I built the env and added to the env folder. ready to pull. thanks-Ali.