diff --git a/README.md b/README.md
index da71d6c2..a93eb3a1 100755
--- a/README.md
+++ b/README.md
@@ -241,11 +241,11 @@ In the current state, we support a single scenario: Data exfiltration to a remot
For the data exfiltration we support 3 variants. The full scenario contains 5 clients (where the attacker can start) and 5 servers where the data that is supposed to be exfiltrated can be located. *scenario1_small* is a variant with a single client (the attacker always starts there) and all 5 servers. *scenario1_tiny* contains only a single server with data. The tiny scenario is trivial and intended only for debugging purposes.
Scenario 1 | Scenario 1 - small | Scenario 1 -tiny |
- | | |
+ | | |
3-nets scenario |
-
+
|
diff --git a/readme_images/scenario 1_small.png b/docs/figures/scenarios/scenario 1_small.png
similarity index 100%
rename from readme_images/scenario 1_small.png
rename to docs/figures/scenarios/scenario 1_small.png
diff --git a/readme_images/scenario_1.png b/docs/figures/scenarios/scenario_1.png
similarity index 100%
rename from readme_images/scenario_1.png
rename to docs/figures/scenarios/scenario_1.png
diff --git a/readme_images/scenario_1_tiny.png b/docs/figures/scenarios/scenario_1_tiny.png
similarity index 100%
rename from readme_images/scenario_1_tiny.png
rename to docs/figures/scenarios/scenario_1_tiny.png
diff --git a/readme_images/three_nets.png b/docs/figures/scenarios/three_nets.png
similarity index 100%
rename from readme_images/three_nets.png
rename to docs/figures/scenarios/three_nets.png
diff --git a/trajectory_paper_task_config.yaml b/trajectory_paper_task_config.yaml
deleted file mode 100644
index caca26e2..00000000
--- a/trajectory_paper_task_config.yaml
+++ /dev/null
@@ -1,94 +0,0 @@
-# Configuration file for the NetSecGame environment
-
-coordinator:
- # Define the conf for all the 'attacker' agents.
- agents:
- attackers:
- goal:
- description: "Exfiltrate data to '213.47.23.195'"
- # Put randomize_goal_every_episode in True if you put any of the goal values in 'random'
- is_any_part_of_goal_random: False
- known_networks: []
- #known_networks: [192.168.1.0/24, 192.168.3.0/24]
- known_hosts: []
- #known_hosts: [192.168.1.1, 192.168.1.2]
- controlled_hosts: []
- #controlled_hosts: [213.47.23.195, 192.168.1.3]
- # Services are defined as a target host where the service must be, and then a description in the form 'name,type,version,is_local'
- known_services: {}
- #known_services: {192.168.1.3: [Local system, lanman server, 10.0.19041, False], 192.168.1.4: [Other system, SMB server, 21.2.39421, False]}
- # In data, put the target host that must have the data and which data in format user,data
- # Example to fix the data in one host
- known_data: {213.47.23.195: [[User1,DataFromServer1]]}
- # Example to fix two data in one host
- #known_data: {213.47.23.195: [[User1,DataFromServer1], [User5,DataFromServer5]]}
- # Example to fix the data in two host
- #known_data: {213.47.23.195: [User1,DataFromServer1], 192.168.3.1: [User3,Data3FromServer3]}
- # Example to ask a random data in a specific server. Putting 'random' in the data, forces the env to randomly choose where the goal data is
- # known_data: {213.47.23.195: [random]}
-
- start_position:
- known_networks: []
- known_hosts: []
- # The attacker must always at least control the CC if the goal is to exfiltrate there
- # Example of fixing the starting point of the agent in a local host
- controlled_hosts: [213.47.23.195, random]
- # Example of asking a random position to start the agent
- # controlled_hosts: [213.47.23.195, random]
- # Services are defined as a target host where the service must be, and then a description in the form 'name,type,version,is_local'
- known_services: {}
- # known_services: {192.168.1.3: [Local system, lanman server, 10.0.19041, False], 192.168.1.4: [Other system, SMB server, 21.2.39421, False]}
- # Same format as before
- known_data: {}
-
- defenders:
- # types are StochasticDefender and NoDefender
- #type: 'StochasticDefender'
- type: 'StochasticWithThreshold'
- # type: 'NoDefender'
- tw_size: 5
- thresholds:
- scan_network: # if both conditions are true, you are never detected
- consecutive_actions: 2 # min amount of consecutive actions you can do without detection
- tw_ratio: 0.25 # min ratio of actions in the tw below which you are not detected
- find_services:
- consecutive_actions: 3
- tw_ratio: 0.3
- exploit_service:
- repeated_actions_episode: 2
- tw_ratio: 0.25
- find_data:
- tw_ratio: 0.5
- repeated_actions_episode: 2
- exfiltrate_data:
- consecutive_actions: 2
- tw_ratio: 0.25
- action_detetection_prob:
- scan_network: 0.05
- find_services: 0.075
- exploit_service: 0.1
- find_data: 0.025
- exfiltrate_data: 0.025
-env:
- # random means to choose the seed in a random way, so it is not fixed
- random_seed: 'random'
- # Or you can fix the seed
- # random_seed: 42
- scenario: 'scenario1'
- max_steps: 100
- store_replay_buffer: True
- use_dynamic_addresses: False
- goal_reward: 100
- detection_reward: -5
- step_reward: -1
- actions:
- scan_network:
- prob_success: 1.0
- find_services:
- prob_success: 1.0
- exploit_service:
- prob_success: 1.0
- find_data:
- prob_success: 1.0
- exfiltrate_data:
- prob_success: 1.0