dstl / YAWNING-TITAN

YAWNING TITAN is an abstract, graph based cyber-security simulation environment that supports the training of intelligent agents for autonomous cyber operations.

dstl/YAWNING-TITAN Issues

Add support for the new OpenAI Gym `step` API interface
Updated a year ago3
[BUG] Action indices randomised on environment initialisation
Closed a year ago5
[BUG] Rendering and GIF saving is broken
Closed a year ago5
yawning_titan.agents.nsa_red doesnt seem to be working (TypeError: 'NSARed' object is not callable)
Updated a year ago1
Suggestion: check if a node is connected to an indirect specific node (e.g., high_value_target)
Updated a year ago3
[BUG] internal reporting for node.isolated may be incorrect
Updated a year ago1
Typo in the Citation section
Closed a year ago1
[BUG] Saved GIFs seem to be zoomed-in on only part of the network
Closed a year ago1
Broken link in documentation
Closed a year ago2
Suggestion: adding the isolated state to observation
Closed a year ago1
Incorrect reward for blue agent reaching max_steps
Closed a year ago1
Isolation cost/reward
Closed a year ago1
Signature of NetworkInterface causing issues in a few files
Closed 2 years ago3
high_value_target not working with lose_when_high_value_target_lost setting (i.e self.gr_loss_hvt is True)
Closed 2 years ago4
Non reproducibility
Closed 2 years ago3
Scanning action not useful as blue agent sees the true compromised state
Closed 2 years ago3
input never an integer in custom_network function - network_creator
Closed 2 years ago3
high_value_target is always "None" if "gr_loss_hvt" = False, network_interface
Closed 2 years ago4