Commit Graph

770 Commits

Author SHA1 Message Date
SunilSamra
6b8cf73207 901 - Added another test and tidied up comments in test_observation_space.py and tidied up comments in observations.py 2023-07-14 14:51:26 +01:00
Marek Wolan
e522e56ff1 Add typehints 2023-07-14 14:43:47 +01:00
Czar.Echavez
fbdb8aab28 #1595:
- Added ability to load sessions via PrimaiteSession
- PrimaiteSession loading test
- Added a NotImplemented RLlib loading for now
- Added the ability to load sessions for hardcoded agents
- Moved Session metadata parsing to utils
2023-07-14 14:14:03 +01:00
Chris McCarthy
8c0ca8cfbc #901 - Dropped temp_primaite_sessiion_2 from conftest.py.
- Re-added the hard-coded mean rewards per episode values from a rpe-trained agent to the deterministic test in test_seeding_and_deterministic_session.py
- Partially tidies up some tests in test_observation_space.py; Still some work to be done on this at a later date.
2023-07-14 14:13:11 +01:00
SunilSamra
4a0d688ae6 901 - fixed test_observation_space.py, added test fixture for test_seeding_and_deterministic_session.py and increased default max number of acls 2023-07-14 12:29:50 +01:00
Marek Wolan
c57ed6edcd Added type hints 2023-07-14 12:01:38 +01:00
Czar Echavez
dce0d10383 #1595: fix poorly merged tests + files 2023-07-14 11:21:59 +01:00
Czar Echavez
a92ef3f4ad #1595: test to make sure that the loaded agent trains + remove unnecessary files + fixing agent save output name 2023-07-14 10:56:28 +01:00
Czar Echavez
bc7c32697f Merge branch 'dev' into feature/1595-finalise-and-test-the-loading-of-trained-agents 2023-07-14 08:39:52 +01:00
Marek Wolan
a923d818d3 Add More Typehint 2023-07-13 18:08:44 +01:00
SunilSamra
0bcaf0696d 901 - removed print statements and merged with dev 2023-07-13 17:14:59 +01:00
SunilSamra
79d77c85c4 Merge remote-tracking branch 'origin/dev' into feature/901-change-functionality-acl-rules 2023-07-13 16:48:02 +01:00
Czar.Echavez
c3023d4d7c #1595 missed hardcoded_abc file in commit 2023-07-13 16:24:30 +01:00
Czar.Echavez
e2d5f0bcff #1595:
- SB3 Agent loading
- rename agent.py -> agent_abc.py
- rename hardcoded.py -> hardcoded_abc.py
- Tests
- Added in test asset that is used to load the SB3 Agent
2023-07-13 16:24:03 +01:00
Marek Wolan
4e4166d4d4 Continue Adding Typehints 2023-07-13 12:25:54 +01:00
SunilSamra
771061a218 901 - fixed test_single_action_space.py test 2023-07-13 11:45:23 +01:00
SunilSamra
ad4198da13 901 - changed acl current obs from list to numpy.array, changed default ACL list in training_config.py to FALSE, and tried to make test_seeding_and_deterministic_session.py test without fixed reward results 2023-07-13 11:04:11 +01:00
Marek Wolan
d2bac4307a Type hint ACLs 2023-07-12 16:58:12 +01:00
SunilSamra
e192d24800 Merge remote-tracking branch 'origin/dev' into feature/901-change-functionality-acl-rules
# Conflicts:
#	src/primaite/acl/access_control_list.py
2023-07-12 10:45:03 +01:00
SunilSamra
ae6c90a670 901 - fixed how acls are added into list with new logic - agent cannot overwrite another acl in the list 2023-07-12 09:47:16 +01:00
Czar.Echavez
e51391b0cf #1595: Moved hardcoded agent into its own file 2023-07-11 15:03:02 +01:00
SunilSamra
6547789d5d 901 - changed implicit_acl_rule from str to enum name 2023-07-11 12:36:22 +01:00
SunilSamra
f14963b6fb Merge remote-tracking branch 'origin/dev' into feature/1566-configure_episode-steps-learn-eval
# Conflicts:
#	src/primaite/config/training_config.py
2023-07-11 11:39:21 +01:00
SunilSamra
728ff01076 1566 - fixed the test_training_config.py test file by removing num_steps from init 2023-07-10 13:24:34 +01:00
SunilSamra
9738d2b889 1566 - added correct num_train_episodes etc values to configs, fixed test_reward.py 2023-07-10 11:25:26 +01:00
Marek Wolan
56f369cfe0 Merge remote-tracking branch 'origin/dev' into bugfix/1587-hardcoded-agent 2023-07-10 09:15:25 +01:00
Marek Wolan
07a0581fce Merge remote-tracking branch 'origin/dev' into feature/1572-fix-docs-formatting 2023-07-09 18:13:57 +01:00
Marek Wolan
aac0e2cc0f Merge remote-tracking branch 'origin/dev' into bugfix/1587-hardcoded-agent 2023-07-09 18:07:30 +01:00
Marek Wolan
105fcaecf4 Removed comment 2023-07-09 18:07:21 +01:00
Marek Wolan
72aef78391 Merged PR 106: Resolve TODOs about documenting functions
## Summary
- Added type hints and docstrings to functions imported from ADSP.
- Imported `get_relevant_rules` which was referenced but didn't exist.
- Removed duplicated function definitions in `agents.utils`

## Test process
The changes in this PR are almost exclusively cosmetic. I can confirm that after adding/removing functions, the unit tests passed fine. I was also able to run the Hardcoded node and ACL agents without problems.

## Checklist
- [x] This PR is linked to a **work item**
- [x] I have performed **self-review** of the code
- [na] I have written **tests** for any new functionality added with this PR
- [na] 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: #1575
2023-07-07 15:10:44 +00:00
Chris McCarthy
1ddfca6459 #1566 - Refactored the test_train_eval_episode_steps.py to sue TempPrimaiteSession.
- Fixed all errors that were caused b fixing the above.
- Some tests still fail, these are for SS to fix.
- Dropped the old run_generic stuff from conftest.py
2023-07-07 15:50:14 +01:00
SunilSamra
4902ccd2b4 Merge remote-tracking branch 'origin/dev' into feature/901-change-functionality-acl-rules 2023-07-07 15:14:05 +01:00
Chris McCarthy
8edb26a65c Merge remote-tracking branch 'origin/dev' into 1566-configure-episode-steps-learn-eval
# Conflicts:
#	src/primaite/agents/rllib.py
2023-07-07 14:34:20 +01:00
SunilSamra
79d98e977b 1566 - added test file and edited configs to include types of num steps and modifed agents to use correct step and episode counts 2023-07-07 14:13:47 +01:00
Marek Wolan
1d1f3f2403 Merge remote-tracking branch 'origin/dev' into feature/1572-fix-docs-formatting 2023-07-07 10:30:11 +01:00
Marek Wolan
5618283cc5 Standardise docstring summary line placement. 2023-07-07 10:28:00 +01:00
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
Marek Wolan
653d76ec62 Added docstrings to class intialisers 2023-07-06 16:08:51 +01:00
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
SunilSamra
3ff081ea71 1566 - added train_episodes, train_steps, eval_episodes and eval_steps to training_config_main.yaml 2023-07-06 11:12:51 +01:00
SunilSamra
7a02661c66 901 - changed how acl rules are added to access control list and added structure to AccessControlList observation 2023-07-06 11:07:21 +01:00
Marek Wolan
30b08fd48b Rescaled default rewards by a factor of 1/10000 2023-07-06 10:51:34 +01:00
Marek Wolan
d9394d274d Updated documentation 2023-07-06 10:34:27 +01:00
Marek Wolan
b9549497d2 Removed duplicated function definitions 2023-07-06 10:23:14 +01:00
Chris McCarthy
f92d2fb65d temp 2023-07-06 10:07:54 +01:00