oxbrbtx/PrimAITE
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
227 Commits 3 Branches 10 Tags
179301e068907e462ee963a3d58ac2310dac7cd4
Commit Graph

150 Commits

Author SHA1 Message Date
Czar Echavez
76997f403e Merge branch 'dev' into feature/1386-enable-a-repeatable-or-deterministic-baseline-test 2023-07-06 22:22:37 +01:00
Christopher McCarthy
5ac196b3cb Merged PR 109: Auto save agent at end of training 
## Summary
* Made RLlib and SB3 agents save at the end of each learning session by default using a common file naming format. Also now agents only checkpoint every n and not on the final episode.

## Test process
*Tests saved agent file in the test_primaite_session test.

## Checklist
- [X] This PR is linked to a **work item**
- [X] I have performed **self-review** of the code
- [X] I have written **tests** for any new functionality added with this PR
- [ ] I have updated the **documentation** if this PR changes or adds functionality
- [X] I have run **pre-commit** checks for code style

Related work items: #1593
 2023-07-06 16:29:48 +00:00
Chris McCarthy
ddabf991ce #1593 - Ran pre-commit hook 2023-07-06 14:18:49 +01:00
Chris McCarthy
1e7f5b62f3 #1963 - Made RLlib and SB3 agents save at the end of each learning session by default using a common file naming format. Also now agents only checkpoint every n and not on the final episode 2023-07-06 13:56:12 +01:00
Marek Wolan
dd8593e489 Change reward to float and divide by 10000 2023-07-06 12:52:14 +01:00
Czar Echavez
bb9bfc50a5 #1386: remove setting of global seed + running pre-commit checks 2023-07-06 12:10:26 +01:00
Chris McCarthy
a35c363345 #1386 - Updated tests in test_seeding_and_deterministic_session.py to use TempPrimaiteSession. 
- Added test_seeded_learning test and test_deterministic_evaluation test.
- Passed config values seed and deterministic to ppo agent
- Dropped deterministic override in evaluate functions
- TempPrimaiteSession now writes files to a UUID folder rather than datetime
- Added seed to Ray RLlib agent setup in rllib.py
- Added seed to SB3 agent setup in sb3.py
 2023-07-06 11:35:44 +01:00
Marek Wolan
30b08fd48b Rescaled default rewards by a factor of 1/10000 2023-07-06 10:51:34 +01:00
Chris McCarthy
f92d2fb65d temp 2023-07-06 10:07:54 +01:00
Czar Echavez
0068092d8b #1386: remove unneeded configs + setting the seed globally + temp test 2023-07-05 15:02:41 +01:00
Czar Echavez
b0c83d7148 #1386: fix saving of agent 2023-07-05 11:41:18 +01:00
Czar Echavez
818d64f330 #1386: fix bug with agent zip file not being saved after run 2023-07-04 16:30:31 +01:00
Czar Echavez
c7de7bf21b Merge branch 'dev' into feature/1386-enable-a-repeatable-or-deterministic-baseline-test 2023-07-04 09:41:07 +01:00
Chris McCarthy
27e22edaf1 #917 - Reinstalled the pre-commit hook 2023-07-03 20:40:38 +01:00
Chris McCarthy
e271a28bf0 #917 - Synced with dev and integrated the new observation space 2023-07-03 20:36:21 +01:00
Chris McCarthy
1716786441 Merge remote-tracking branch 'origin/dev' into feature/917_Integrate_with_RLLib 
# Conflicts:
#	src/primaite/config/_package_data/training/training_config_main.yaml
#	src/primaite/environment/primaite_env.py
#	src/primaite/main.py
#	src/primaite/transactions/transaction.py
#	src/primaite/transactions/transactions_to_file.py
 2023-07-03 19:51:52 +01:00
Chris McCarthy
c36ddfa03f #917 - Synced with dev (at the point of random red agent) 2023-07-03 17:25:21 +01:00
Czar Echavez
409743dee9 Merge branch 'dev' into feature/1386-enable-a-repeatable-or-deterministic-baseline-test 2023-07-03 16:56:44 +01:00
Chris McCarthy
d55225dd41 Merge remote-tracking branch 'origin/dev' into feature/917_Integrate_with_RLLib 
# Conflicts:
#	src/primaite/config/_package_data/training/training_config_main.yaml
#	src/primaite/environment/primaite_env.py
 2023-07-03 15:07:09 +01:00
Marek Wolan
93881e5d2c Merge remote-tracking branch 'origin/dev' into feature/1558-flatten-spaces 2023-07-03 15:03:10 +01:00
Czar Echavez
a7913487b8 #1522: create_random_red_agent -> _create_random_red_agent + converting NodeStateInstructionRed into a dataclass 2023-07-03 13:36:14 +01:00
Czar Echavez
befd183b2c #1522: refactor red_agent_identifier -> random_red_agent so that it is a boolean + documentation 2023-07-03 12:18:58 +01:00
Christopher McCarthy
7fe46ef99c Apply suggestions from code review 2023-07-03 10:47:26 +00:00
Czar Echavez
6b4530bded #1522: run pre-commit 2023-07-03 10:08:25 +01:00
Czar Echavez
68457aa0b2 #1522: added a check for existing links in laydown + test that checks if red agent instructions are random 2023-07-03 09:46:52 +01:00
Marek Wolan
046937d838 Apply suggestions from code review 2023-07-03 08:00:51 +00:00
Chris McCarthy
06d5004695 #917 - Dropped VerboseLevel in enums.py and changed OutputVerboseLevel to SB3OutputVerboseLevel 2023-06-30 17:09:50 +01:00
Chris McCarthy
e11fd2ced4 #917 - Fixed the RLlib integration 
- Dropped support for overriding the num_episodes and num_steps at the agent level. It's just not needed and will add complexity when overriding and writing output files.
 2023-06-30 16:52:57 +01:00
Marek Wolan
7e6fe2759b Fix flattening when there are no components. 2023-06-30 15:43:15 +01:00
Marek Wolan
d86489a9c2 revert unnecessary changes. 2023-06-30 13:16:30 +01:00
Chris McCarthy
00185d3dad #917 - Fixed primaite_config.yaml issue in cli.py 
- Added kaleido to deps in pyproject.toml
 2023-06-30 11:40:26 +01:00
Marek Wolan
99ba05c6ee Remove redundant cols from transactions 2023-06-30 10:41:56 +01:00
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
Marek Wolan
c9f58fdb2a Fix observation representation in transactions 2023-06-29 15:26:07 +01:00
Czar Echavez
10e432eb01 #1522: fixing create random red agent function 2023-06-29 15:03:11 +01:00
Czar Echavez
15b3bad5d4 Merge branch 'dev' into feature/1522-Random-Red-Agent-Behaviour 2023-06-29 14:17:41 +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
edab1a393d Merge remote-tracking branch 'origin/dev' into feature/917_Integrate_with_RLLib 
# Conflicts:
#	src/primaite/config/training_config.py
#	src/primaite/main.py
 2023-06-28 10:11:03 +01:00
Marek Wolan
d28db68c02 Merged PR 95: Apply precommits and add precommit to build pipeline 
## Summary
The code changes are purely cosmetic- the result of applying pre-commit to all our files. I also added a pre-commit step to the build pipeline to reject non-conforming PRs

## Test process
I saw that the build pipeline passes with this new step.

## Checklist
- [ ] This PR is linked to a **work item**
- [x] I have performed **self-review** of the code
- [ ] I have written **tests** for any new functionality added with this PR
- [ ] I have updated the **documentation** if this PR changes or adds functionality
- [x] I have run **pre-commit** checks for code style

Related work items: #1557
 2023-06-28 08:14:49 +00:00
Chris McCarthy
20b65ae9ab Merge remote-tracking branch 'origin/bugfix/1554-fix-not-learning-iers' into feature/917_Integrate_with_RLLib 2023-06-27 15:56:56 +01:00
Marek Wolan
afe5bf8fe8 Merge branch 'dev' into feature/build-pipeline-precommit 2023-06-27 15:49:49 +01:00
Marek Wolan
349a18a4eb Fix ier reward calculation 2023-06-27 15:27:56 +01:00
Czar Echavez
be041f5e5c Merge branch 'dev' into feature/1386-enable-a-repeatable-or-deterministic-baseline-test 2023-06-27 14:16:10 +01:00
Marek Wolan
beae1e5c4f Cosmetic changes to satisfy pre-commit 2023-06-27 13:06:10 +01:00
Marek Wolan
de91a50581 Improve readability 2023-06-27 12:56:15 +01:00