Marek Wolan
c5d7d55747
Change reward to float and divide by 10000
2023-07-06 12:52:14 +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
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
1d3778f400
#917 - Overhauled transaction and mean reward writing.
...
- Separated out learning outputs from evaluation outputs
2023-06-28 16:34:00 +01:00
Marek Wolan
cffdcdc0d2
Fix ier reward calculation
2023-06-27 15:27:56 +01:00
Marek Wolan
0bff2d2f36
Improve readability
2023-06-27 12:56:15 +01:00
Marek Wolan
79ecb8e0b9
More descriptive debug msg
2023-06-27 12:44:42 +01:00
Marek Wolan
ebc0a28460
rename to prevent confusion
2023-06-27 10:45:45 +00:00
Marek Wolan
e2d6abf833
apply pre-commits
2023-06-27 11:20:18 +01:00
Marek Wolan
feead2cd44
Fix reference IERs
2023-06-27 11:10:21 +01:00
Sunil Samra
83694fe537
Apply suggestions from code review
2023-05-31 08:09:09 +00:00
SunilSamra
0483eeca82
1443 - changed IF statements from if initial ... if reference to if reference ... if final to compare the final state (state after red and blue actions) with the reference state (state with no red or blue action and with green normal network traffic occurring)
2023-05-30 11:40:40 +01:00
Chris McCarthy
6245ad9298
#1355 - Carried out full renaming in node.py, active_node.py, passive_node.py, and service_node.py to make params and variable names explicit.
...
- Made the same renaming in the yaml laydown config files.
- Added Type hints wherever I've been.
- Added a custom NodeType in custom_typing.py to encompass the Union of ActiveNode, PassiveNode, ServiceNode.
2023-05-25 21:03:11 +01:00
Chris McCarthy
ddb6adae2b
#902 - replaced 'final_node_<placeholder>' with 'reference_node_<placeholder>' in methods for scoring of os_state, file_system_state, service state and operating state. This fixed the reward function so it is checked at each step for node operating system state, operating state, file system state and service state.
...
- Added unit tests.
2023-05-25 14:05:53 +01:00
Chris McCarthy
71f33ed44e
Ran pre-commit hook on all files and performed changes to fix flake8 failures
2023-05-25 11:42:19 +01:00
Chris McCarthy
9bd7aade43
Package restructuring
2023-05-25 10:31:37 +01:00
