Commit Graph

59 Commits

Author SHA1 Message Date
SunilSamra
0ab4dab72a 901 - fixed test_single_action_space.py test 2023-07-13 11:45:23 +01:00
SunilSamra
f8cb18c654 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
SunilSamra
06c20f6984 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
350b3db3f6 901 - changed implicit_acl_rule from str to enum name 2023-07-11 12:36:22 +01:00
SunilSamra
35b481a2f3 Merge remote-tracking branch 'origin/dev' into feature/901-change-functionality-acl-rules 2023-07-07 15:14:05 +01:00
Marek Wolan
7e0eee5d73 Merge remote-tracking branch 'origin/dev' into feature/1572-fix-docs-formatting 2023-07-07 10:30:11 +01:00
Marek Wolan
f4b98542b6 Standardise docstring summary line placement. 2023-07-07 10:28:00 +01:00
Czar Echavez
04e52453b1 Merge branch 'dev' into feature/1386-enable-a-repeatable-or-deterministic-baseline-test 2023-07-06 22:22:37 +01:00
Marek Wolan
86725064ec Added docstrings to class intialisers 2023-07-06 16:08:51 +01:00
Marek Wolan
c5d7d55747 Change reward to float and divide by 10000 2023-07-06 12:52:14 +01:00
Marek Wolan
e174db5d9e Rescaled default rewards by a factor of 1/10000 2023-07-06 10:51:34 +01:00
Czar Echavez
713225b432 #1386: remove unneeded configs + setting the seed globally + temp test 2023-07-05 15:02:41 +01:00
SunilSamra
f121b0e21c 901 - merged with dev 2023-07-05 11:34:15 +01:00
Marek Wolan
cda9819e72 Add blank lines at the end of file. 2023-07-05 09:22:49 +01:00
Marek Wolan
eac79e0941 Add missing module level docstrings. 2023-07-05 09:19:58 +01:00
SunilSamra
3f440c0a28 901 - updated observations.py to change and add new mapping of ACL rules to represent no rule present in list 2023-07-05 09:08:03 +01:00
Marek Wolan
5e270c7673 Format docstrings 2023-07-04 11:11:52 +01:00
Czar Echavez
410afc1d40 Merge branch 'dev' into feature/1386-enable-a-repeatable-or-deterministic-baseline-test 2023-07-04 09:41:07 +01:00
Chris McCarthy
820f436f8e 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
7816e94f83 #917 - Synced with dev (at the point of random red agent) 2023-07-03 17:25:21 +01:00
Czar Echavez
a883e45bbf Merge branch 'dev' into feature/1386-enable-a-repeatable-or-deterministic-baseline-test 2023-07-03 16:56:44 +01:00
Chris McCarthy
d2764d53cc 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
12c18adeb1 Merge remote-tracking branch 'origin/dev' into feature/1558-flatten-spaces 2023-07-03 15:03:10 +01:00
Czar Echavez
0943e9511b #1522: refactor red_agent_identifier -> random_red_agent so that it is a boolean + documentation 2023-07-03 12:18:58 +01:00
Chris McCarthy
16534237e0 #917 - Dropped VerboseLevel in enums.py and changed OutputVerboseLevel to SB3OutputVerboseLevel 2023-06-30 17:09:50 +01:00
Chris McCarthy
27ca53878a #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
975ebd6de2 revert unnecessary changes. 2023-06-30 13:16:30 +01:00
Czar Echavez
3e691b4f46 #1522: remove numpy randomisation + added random red agent config 2023-06-30 10:37:23 +01:00
Chris McCarthy
d5402cdce8 #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
73015802ec #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
7f912df383 #917 - Began the process of reloading existing agents into the session 2023-06-28 19:54:00 +01:00
Chris McCarthy
1d3778f400 #917 - Overhauled transaction and mean reward writing.
- Separated out learning outputs from evaluation outputs
2023-06-28 16:34:00 +01:00
Chris McCarthy
7482192046 #917 - Synced with dev and added better logging 2023-06-28 12:01:01 +01:00
Marek Wolan
9666b92caa Attempt to add flat spaces 2023-06-28 11:07:45 +01:00
Chris McCarthy
498e6a7ac1 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
be7d0e1745 Cosmetic changes to satisfy pre-commit 2023-06-27 13:06:10 +01:00
Czar Echavez
fb50b8becf #1386: Apply suggestions from code review - make seed an optional variable 2023-06-23 07:57:31 +00:00
Brian Kanyora
e0f3d61f65 feature\1522:
Create random red agent behaviour.
2023-06-22 15:34:13 +01:00
Chris McCarthy
7f1c4ce036 #917 - Updated main config 2023-06-22 14:10:38 +01:00
Chris McCarthy
a2cc4233b5 #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
SunilSamra
df42a791c9 901 - changed ACL instantiation and changed acl t private _acl (list not dict) attribute, added laydown_ACL.yaml for testing, fixed encoding of acl rules to integers for obs space, added ACL position to node action space and added generic test where agents adds two ACL rules. 2023-06-20 11:47:20 +01:00
Czar Echavez
db67a829d5 #1386: added documentation + dealing with pre-commit checks 2023-06-20 11:19:05 +01:00
Czar Echavez
0ab4520904 #1386: added the ability to set deterministic and seeding RNG when training and evaluating + the fix provided in #1535 2023-06-20 10:41:30 +01:00
Chris McCarthy
03ae4884e0 #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
23bafde457 #917 - Integrated both SB3 and RLlib agents into PrimaiteSession 2023-06-19 20:27:08 +01:00
Chris McCarthy
c2c396052f #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
SunilSamra
c6a947fbaf 901 - started testing for observation space 2023-06-13 16:23:32 +01:00
SunilSamra
5b59642695 901 - added max_acl_rules, implicit_acl_rule and apply_implicit rule to main_config, changed observations.py for ACLs to match the action space for ACLs, added position of acl rule to ACL action type 2023-06-13 14:51:55 +01:00
SunilSamra
cf64990cff 901 - added changes back to ticket 2023-06-13 09:45:45 +01:00
Chris McCarthy
eb3368edd6 temp commit 2023-06-13 09:42:54 +01:00