RouteRL-URB Homecoming - #74
Merged
Merged
Conversation
- Generating paths only for demanded OD pairs, and not all OD combinations. - Path visualization made optional. - Gridlocks occur in high demands and small networks. This is now resolved with stuck vehicle teleportation. - Teleporting vehicles are rewarded (penalized) by simulation length. - params.json is renamed to defaults.json for clarity. - Teleportation treshold is added as a parameter. - New folder of tutorials, including a relistic demand from Ingolstadt network.
Refer to commit messages for details.
- Before demand-based path gen was conditioned on the existence of agents.csv. - agents.csv might exist even when user doesn't want to use it (create_agents=True) - Therefore demand-based path gen is now conditioned on create_agents argument. - Docstrings updated.
- Updated learning_model.py with new changes from RoutingZoo. - Model names and parameters are updated in the registry, keychain and defaults.
Human learning updates and changes accordingly
Default agent actions. When the `default_action` attribute is set, the (human) agent will choose that action deterministically.
Feat/action masks
Support for MultiSyncDataCollector from torch rl and additional simulator parameters.
Add SUMO-based observations
Custom objectives
Member
Author
|
@mikolajRams There were some last minute additions, you might want to rebase your branch. |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
7 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Syncing the changes made in the RouteRL-URB branch with the OG repo. Automated notes:
This pull request introduces several important updates to the documentation, metadata, and example configuration for the RouteRL project. The changes improve clarity and accuracy in the documentation, update project metadata to reflect the latest release and publication, and revise the main example script for better demonstration of human and machine agent training phases.
Documentation and Model Naming Improvements:
The observation and human model documentation has been expanded and clarified, including detailed descriptions of new observation classes such as
TripInfoWithETA,TripInfoWithETAMaskNorm,TripInfoWithETARouteCongestion,RouteCongestion, andTripInfoWithETASumo. Human model class references have been updated to match the current codebase, and the order of model presentation has been revised for clarity. [1] [2] [3] [4] [5]The PettingZoo environment documentation was renamed to "Traffic environment" for clarity, and the GitHub project link in the docs index was corrected. [1] [2]
Project Metadata and Citation Updates:
The
CITATION.cfffile was updated to version 1.2.0, with corrected author formatting, a new preferred citation referencing the published SoftwareX article, and version/date updates. [1] [2]The
README.mdwas revised with a new project introduction, updated badges and image links, a new citation section referencing the published article, and expanded credits. [1] [2] [3]Example Script and Configuration Updates:
main.py) was updated to use the "gawron" human model, refactored thenew_machines_after_mutationparameter, and improved the plotting phase configuration for clearer experiment tracking. [1] [2]