Moving the max step logic #3432
Closed
Conversation
This file contains hidden or 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
* updating version number * fixing version numbers
* clarify curriculum and behavior name * doc some other missing fields too
* Update Learning-Environment-Create-New.md (#3356) * Update Learning-Environment-Create-New.md In the "Final Editor Setup" , I think their should be a Step to add Decision Parameters Script and it says Decision Period from 1 to 20. Without this their was no action taken by the RolerAgent. After adding this step it worked for me. * Update docs/Learning-Environment-Create-New.md Co-Authored-By: Chris Elion <[email protected]> * Update docs/Learning-Environment-Create-New.md Co-Authored-By: Chris Elion <[email protected]> Co-authored-by: Chris Elion <[email protected]> * migration fixes Co-authored-by: Medhavi Monish <[email protected]>
* clean up examples and tests * more cleanup * m_UseChildSensors
* Fix ballance ball 100 reward * Re-test * Add test for maxSteps and number of AgentActions Co-authored-by: Chris Elion <[email protected]>
* landing page links to latest_release docs * fix localized links * previous releases * change wording * script to make the table
…3417) * """""Fixing"""""" * Update gym-unity/gym_unity/envs/__init__.py Co-Authored-By: Chris Elion <[email protected]> * Update gym-unity/gym_unity/envs/__init__.py Co-Authored-By: Chris Elion <[email protected]> * addressing comments * Update gym-unity/gym_unity/envs/__init__.py Co-Authored-By: Chris Elion <[email protected]> * Update gym-unity/gym_unity/envs/__init__.py Co-Authored-By: Chris Elion <[email protected]> * Update gym-unity/gym_unity/envs/__init__.py Co-Authored-By: Chris Elion <[email protected]> * bug fix * Fixing the test * gym multiagent comments (#3421) * rename and comments * enumerate Co-authored-by: Chris Elion <[email protected]>
* Fix clear update buffer when trainer stops training, add test * Fix buffer changing types when truncated
- Created a new Academy Event called AgentIncrementStep to be called before SetStatus - Implemented the AgentSteping logic
chriselion
reviewed
Feb 14, 2020
| @@ -113,6 +113,9 @@ public bool IsCommunicatorOn | |||
| // Signals to all the listeners that the academy is being destroyed | |||
| internal event Action DestroyAction; | |||
|
|
|||
| // Signals the Agent that a new step is about to start | |||
There was a problem hiding this comment.
Suggested change
| // Signals the Agent that a new step is about to start | |
| // Signals the Agent that a new step is about to start. This will mark the Agent as Done if it has reached its maxSteps. |
chriselion
reviewed
Feb 14, 2020
| @@ -384,6 +387,8 @@ public void EnvironmentStep() | |||
| ForcedFullReset(); | |||
| } | |||
|
|
|||
| AgentIncrementStep?.Invoke(); | |||
There was a problem hiding this comment.
Hmm, for on-demand decision, this might still have the same problem of an Agent being marked to request a decision, and that getting cleared if the Agent hits maxSteps.
I forget, is there a reason we can't do this last?
There was a problem hiding this comment.
I see, this would happen if the user does not use the decision requester. I will make some experiments to determine if we can do this last as it would make most sense.
…it the tests but I think they are now closer to what we want
10 tasks
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.
Based of the release branch