Commit Graph

64 Commits

Author SHA1 Message Date
Czar Echavez
4e1e0ef4b4 #1522: remove numpy randomisation + added random red agent config 2023-06-30 10:37:23 +01:00
Chris McCarthy
cf09202e96 #917 - Added tensorflow to main deps for RLlib.
- Dropped support for Python 3.11 due to not supported on Ray RLlib.
- Made release pipeline only run once as we're now no longer using pure path wheels.
2023-06-30 10:24:59 +01:00
Chris McCarthy
7b1f889415 #917 - Integrated the PrimaiteSession into all tests.
- Ran a full pre-commit hook and thus encountered tons of fixes required
2023-06-30 09:08:13 +01:00
Chris McCarthy
b6d93ad33f #917 - Began the process of reloading existing agents into the session 2023-06-28 19:54:00 +01:00
Chris McCarthy
4866722911 #917 - Overhauled transaction and mean reward writing.
- Separated out learning outputs from evaluation outputs
2023-06-28 16:34:00 +01:00
Chris McCarthy
a9ebfd7917 #917 - Synced with dev and added better logging 2023-06-28 12:01:01 +01:00
Marek Wolan
e086d419ad Attempt to add flat spaces 2023-06-28 11:07:45 +01:00
Chris McCarthy
8f6e930ba2 #917 - Updated main config 2023-06-22 14:10:38 +01:00
Chris McCarthy
7b0f47d6f8 #917 -Finished integrating all agents to either train (policy agents) or evaluate (hard-coded agents). Still some fixing up to do, tidying up, loading etc. also docs. But this is all now working. 2023-06-20 16:06:55 +01:00
Chris McCarthy
10c94954a5 #917 - Almost there. All output files being writen for SB3/RLLIB PPO & A2C. Just need to bring in the hardcoded agents then update the testa and docs. 2023-06-19 21:53:25 +01:00
Chris McCarthy
3670f16766 #917 - Integrated both SB3 and RLlib agents into PrimaiteSession 2023-06-19 20:27:08 +01:00
Chris McCarthy
c09874edbe #917 - Got RLlib fully training in PrimAITE. Started integrating the the other agents into the Session class 2023-06-18 22:40:56 +01:00
Chris McCarthy
3a5d982991 #915 - Synced with dev to bring in changes from #898 2023-06-09 13:11:14 +01:00
Chris McCarthy
98fc1e4c71 #915 - Created app dirs and set as constants in the top-level init.
- renamed _config_values_main to training_config.py and renamed the ConfigValuesMain class to TrainingConfig.
Moved training_config.py to src/primaite/config/training_config.py
- Renamed all training config yaml file keys to make creating an instance of TrainingConfig easier.
Moved action_type and num_steps over to the training config.
- Decoupled the training config and lay down config.
- Refactored main.py so that it can be ran from CLI and can take a training config path and a lay down config path.
- refactored all outputs so that they save to the session dir.
- Added some necessary setup scripts that handle creating app dirs, fronting example config files to the user, fronting demo notebooks to the user, performing clean-up in between installations etc.
- Added functions that attempt to retrieve the file path of users example config files that have been fronted by the primaite setup.
- Added logging config and a getLogger function in the top-level init.
- Refactored all logs entries logged to use a logger using the primaite logging config.
- Added basic typer CLI for doing things like setup, viewing logs, viewing primaite version, running a basic session.
- Updated test to use new features and config structures.
- Began updating docs. More to do here.
2023-06-07 22:40:16 +01:00