Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Conversation

@bozo-bud
Copy link
Collaborator

Description

Added files and functions needed to implement a new Actor to Critic algorithm using Stable-baseline 3.

Type of Change

Additions were made to the following files:
-rl_scripts/agents/base_agent.py
-rl_scripts/args/general_args.py
-rl_scripts/args/regirstrly_args.py
-rl_scripts/helpers/setup_helpers.py

The following files were added:
-rl_scripts/algorithms/a2c.py
-sb3_scripts/yml/a2c.yml

  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • This change requires a documentation update

How has this change been tested?

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Also, list any relevant details for your test configuration.

No test configurations have been added at this time.

Does change comply with project standards and guideline?

Standards and guidelines can be found on the Project Homepage.

  • Commit formatting
  • Versioning
  • Code style
  • Coding guidelines
  • Unit Testing

@ryanmccann1024 ryanmccann1024 force-pushed the ryan_drl_path_agents branch 2 times, most recently from 1f52b86 to 9afabc1 Compare March 4, 2025 18:57
Copy link
Collaborator

@ryanmccann1024 ryanmccann1024 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Overall I think it's good for a merge if there were no errors. Double check after addressing the comment and merging. Please lint scripts, if there are any errors in unit tests, it's ok to comment them out temporarily to merge.

ryanmccann1024 and others added 24 commits March 21, 2025 15:05
Requests' status dictionary was not being reset.
Also, add test and plot modules for RL.
Also, change some script names for clarity or unnecessary length.
We were not tracking the algorithm name properly.

Also, add an excel module.
Also change seed vs. reward funciton.
We didn't return properly for the SB3 callback, leading to a short episode 'hidden' episode leading to an impossible reward in the first episode in the next trial.
Have q_learning save in the same format as the bandits.
We weren't plotting for all algorithms.
@bozo-bud bozo-bud merged commit f02e502 into ryan_drl_path_agents Mar 22, 2025
2 of 6 checks passed
@ryanmccann1024 ryanmccann1024 deleted the a2c_implement branch August 13, 2025 15:46
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants