cage-challenge-4
cage-challenge-4 copied to clipboard
cage-challenge
The TTCP CAGE Challenges are a series of public challenges instigated to foster the development of autonomous cyber defensive agents. This CAGE Challenge 4 (CC4) returns to a defence industry enterpri...
By default, the `RewardCalculator` class will collect the current true state of the environment to pass on to each reward calculator subclass. https://github.com/cage-challenge/cage-challenge-4/blob/313bf330e5229663606de08df0d0d5135b55961d/CybORG/Shared/RewardCalculator.py#L39-L45 However, neither BlueRewardMachine nor EmptyRewardCalculator use this...
Both reward calculators (BlueRewardMachine and EmptyRewardCalculator) never use the `current_state` that is passed to the `calculate_reward` method. The collection of this state represents a major allocation of execution time during...
These are just minor things found in GreenAccessService.py that relate to corner cases. On line 112, ```if len(reachable_hosts) < 0``` this can never happen as len is always greater than...
Metadata
Owner
Metadata
The TTCP CAGE Challenges are a series of public challenges instigated to foster the development of autonomous cyber defensive agents. This CAGE Challenge 4 (CC4) returns to a defence industry enterpri...