oxbrbtx/PrimAITE
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

#2912 - Merge in changes on target branch

Browse Source
This commit is contained in:
Charlie Crane
2025-01-03 14:48:18 +00:00
parent ab2dd6ca27 eb91721518
commit e653afaa4c
407 changed files with 664 additions and 671 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/primaite/game/__init__.py
View File

@@ -1,2 +1,2 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
"""PrimAITE Game Layer."""

2
src/primaite/game/agent/__init__.py
View File

@@ -1 +1 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK

2
src/primaite/game/agent/agent_log.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
import logging
from pathlib import Path

2
src/primaite/game/agent/interface.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
"""Interface for agents."""
from abc import ABC, abstractmethod
from typing import Any, Dict, List, Optional, Tuple, TYPE_CHECKING

2
src/primaite/game/agent/observations/__init__.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
# flake8: noqa
# Pre-import all the observations when we load up the observations module so that they can be resolved by the parser.
from primaite.game.agent.observations.acl_observation import ACLObservation

2
src/primaite/game/agent/observations/acl_observation.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
from __future__ import annotations
from ipaddress import IPv4Address

2
src/primaite/game/agent/observations/file_system_observations.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
from __future__ import annotations
from typing import Dict, Iterable, List, Optional

2
src/primaite/game/agent/observations/firewall_observation.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
from __future__ import annotations
from typing import Dict, List, Optional

2
src/primaite/game/agent/observations/host_observations.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
from __future__ import annotations
from typing import Dict, List, Optional

2
src/primaite/game/agent/observations/link_observation.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
from __future__ import annotations
from typing import Any, Dict, List

2
src/primaite/game/agent/observations/nic_observations.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
from __future__ import annotations
from typing import Dict, List, Optional

2
src/primaite/game/agent/observations/node_observations.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
from __future__ import annotations
from typing import Dict, List, Optional

2
src/primaite/game/agent/observations/observation_manager.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
from __future__ import annotations
from typing import Any, Dict, List, Optional

2
src/primaite/game/agent/observations/observations.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
"""Manages the observation space for the agent."""
from abc import ABC, abstractmethod
from typing import Any, Dict, Iterable, Optional, Type, Union

2
src/primaite/game/agent/observations/router_observation.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
from __future__ import annotations
from typing import Dict, List, Optional

2
src/primaite/game/agent/observations/software_observation.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
from __future__ import annotations
from typing import Dict

377
src/primaite/game/agent/rewards.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
"""
Manages the reward function for the agent.
@@ -27,9 +27,10 @@ the structure:
service_ref: web_server_database_client
```
"""
from abc import abstractmethod
from typing import Callable, Dict, Iterable, List, Optional, Tuple, Type, TYPE_CHECKING, Union
from abc import ABC, abstractmethod
from typing import Any, Callable, ClassVar, Dict, Iterable, List, Optional, Tuple, Type, TYPE_CHECKING, Union
from pydantic import BaseModel
from typing_extensions import Never
from primaite import getLogger
@@ -42,25 +43,26 @@ _LOGGER = getLogger(__name__)
WhereType = Optional[Iterable[Union[str, int]]]
class AbstractReward:
class AbstractReward(BaseModel):
"""Base class for reward function components."""
@abstractmethod
def calculate(self, state: Dict, last_action_response: "AgentHistoryItem") -> float:
"""Calculate the reward for the current state.
config: "AbstractReward.ConfigSchema"
:param state: Current simulation state
:type state: Dict
:param last_action_response: Current agent history state
:type last_action_response: AgentHistoryItem state
:return: Reward value
:rtype: float
"""
return 0.0
class ConfigSchema(BaseModel, ABC):
"""Config schema for AbstractReward."""
type: str
_registry: ClassVar[Dict[str, Type["AbstractReward"]]] = {}
def __init_subclass__(cls, identifier: str, **kwargs: Any) -> None:
super().__init_subclass__(**kwargs)
if identifier in cls._registry:
raise ValueError(f"Duplicate reward {identifier}")
cls._registry[identifier] = cls
@classmethod
@abstractmethod
def from_config(cls, config: dict) -> "AbstractReward":
def from_config(cls, config: Dict) -> "AbstractReward":
"""Create a reward function component from a config dictionary.
:param config: dict of options for the reward component's constructor
@@ -68,11 +70,28 @@ class AbstractReward:
:return: The reward component.
:rtype: AbstractReward
"""
return cls()
if config["type"] not in cls._registry:
raise ValueError(f"Invalid reward type {config['type']}")
reward_class = cls._registry[config["type"]]
reward_obj = reward_class(config=reward_class.ConfigSchema(**config))
return reward_obj
@abstractmethod
def calculate(self, state: Dict, last_action_response: "AgentHistoryItem") -> float:
"""Calculate the reward for the current state.
:param state: Current simulation state
:type state: Dict
:param last_action_response: Current agent history state
:type last_action_response: AgentHistoryItem state
:return: Reward value
:rtype: float
"""
return 0.0
class DummyReward(AbstractReward):
"""Dummy reward function component which always returns 0."""
class DummyReward(AbstractReward, identifier="DUMMY"):
"""Dummy reward function component which always returns 0.0."""
def calculate(self, state: Dict, last_action_response: "AgentHistoryItem") -> float:
"""Calculate the reward for the current state.
@@ -86,41 +105,21 @@ class DummyReward(AbstractReward):
"""
return 0.0
@classmethod
def from_config(cls, config: dict) -> "DummyReward":
"""Create a reward function component from a config dictionary.
:param config: dict of options for the reward component's constructor. Should be empty.
:type config: dict
:return: The reward component.
:rtype: DummyReward
"""
return cls()
class DatabaseFileIntegrity(AbstractReward):
class DatabaseFileIntegrity(AbstractReward, identifier="DATABASE_FILE_INTEGRITY"):
"""Reward function component which rewards the agent for maintaining the integrity of a database file."""
def __init__(self, node_hostname: str, folder_name: str, file_name: str) -> None:
"""Initialise the reward component.
config: "DatabaseFileIntegrity.ConfigSchema"
location_in_state: List[str] = [""]
reward: float = 0.0
:param node_hostname: Hostname of the node which contains the database file.
:type node_hostname: str
:param folder_name: folder which contains the database file.
:type folder_name: str
:param file_name: name of the database file.
:type file_name: str
"""
self.location_in_state = [
"network",
"nodes",
node_hostname,
"file_system",
"folders",
folder_name,
"files",
file_name,
]
class ConfigSchema(AbstractReward.ConfigSchema):
"""ConfigSchema for DatabaseFileIntegrity."""
type: str = "DATABASE_FILE_INTEGRITY"
node_hostname: str
folder_name: str
file_name: str
def calculate(self, state: Dict, last_action_response: "AgentHistoryItem") -> float:
"""Calculate the reward for the current state.
@@ -132,6 +131,17 @@ class DatabaseFileIntegrity(AbstractReward):
:return: Reward value
:rtype: float
"""
self.location_in_state = [
"network",
"nodes",
self.config.node_hostname,
"file_system",
"folders",
self.config.folder_name,
"files",
self.config.file_name,
]
database_file_state = access_from_nested_dict(state, self.location_in_state)
if database_file_state is NOT_PRESENT_IN_STATE:
_LOGGER.debug(
@@ -148,44 +158,21 @@ class DatabaseFileIntegrity(AbstractReward):
else:
return 0
@classmethod
def from_config(cls, config: Dict) -> "DatabaseFileIntegrity":
"""Create a reward function component from a config dictionary.
:param config: dict of options for the reward component's constructor
:type config: Dict
:return: The reward component.
:rtype: DatabaseFileIntegrity
"""
node_hostname = config.get("node_hostname")
folder_name = config.get("folder_name")
file_name = config.get("file_name")
if not (node_hostname and folder_name and file_name):
msg = f"{cls.__name__} could not be initialised with parameters {config}"
_LOGGER.error(msg)
raise ValueError(msg)
return cls(node_hostname=node_hostname, folder_name=folder_name, file_name=file_name)
class WebServer404Penalty(AbstractReward):
class WebServer404Penalty(AbstractReward, identifier="WEB_SERVER_404_PENALTY"):
"""Reward function component which penalises the agent when the web server returns a 404 error."""
def __init__(self, node_hostname: str, service_name: str, sticky: bool = True) -> None:
"""Initialise the reward component.
config: "WebServer404Penalty.ConfigSchema"
location_in_state: List[str] = [""]
reward: float = 0.0
:param node_hostname: Hostname of the node which contains the web server service.
:type node_hostname: str
:param service_name: Name of the web server service.
:type service_name: str
:param sticky: If True, calculate the reward based on the most recent response status. If False, only calculate
the reward if there were any responses this timestep.
:type sticky: bool
"""
self.sticky: bool = sticky
self.reward: float = 0.0
"""Reward value calculated last time any responses were seen. Used for persisting sticky rewards."""
self.location_in_state = ["network", "nodes", node_hostname, "services", service_name]
class ConfigSchema(AbstractReward.ConfigSchema):
"""ConfigSchema for WebServer404Penalty."""
type: str = "WEB_SERVER_404_PENALTY"
node_hostname: str
service_name: str
sticky: bool = True
def calculate(self, state: Dict, last_action_response: "AgentHistoryItem") -> float:
"""Calculate the reward for the current state.
@@ -197,6 +184,13 @@ class WebServer404Penalty(AbstractReward):
:return: Reward value
:rtype: float
"""
self.location_in_state = [
"network",
"nodes",
self.config.node_hostname,
"services",
self.config.service_name,
]
web_service_state = access_from_nested_dict(state, self.location_in_state)
# if webserver is no longer installed on the node, return 0
@@ -211,54 +205,27 @@ class WebServer404Penalty(AbstractReward):
return 1.0 if status == 200 else -1.0 if status == 404 else 0.0
self.reward = sum(map(status2rew, codes)) / len(codes) # convert form HTTP codes to rewards and average
elif not self.sticky: # there are no codes, but reward is not sticky, set reward to 0
elif not self.config.sticky: # there are no codes, but reward is not sticky, set reward to 0
self.reward = 0.0
else: # skip calculating if sticky and no new codes. instead, reuse last step's value
pass
return self.reward
@classmethod
def from_config(cls, config: Dict) -> "WebServer404Penalty":
"""Create a reward function component from a config dictionary.
:param config: dict of options for the reward component's constructor
:type config: Dict
:return: The reward component.
:rtype: WebServer404Penalty
"""
node_hostname = config.get("node_hostname")
service_name = config.get("service_name")
if not (node_hostname and service_name):
msg = (
f"{cls.__name__} could not be initialised from config because node_name and service_ref were not "
"found in reward config."
)
_LOGGER.warning(msg)
raise ValueError(msg)
sticky = config.get("sticky", True)
return cls(node_hostname=node_hostname, service_name=service_name, sticky=sticky)
class WebpageUnavailablePenalty(AbstractReward):
class WebpageUnavailablePenalty(AbstractReward, identifier="WEBPAGE_UNAVAILABLE_PENALTY"):
"""Penalises the agent when the web browser fails to fetch a webpage."""
def __init__(self, node_hostname: str, sticky: bool = True) -> None:
"""
Initialise the reward component.
config: "WebpageUnavailablePenalty.ConfigSchema"
reward: float = 0.0
location_in_state: List[str] = [""] # Calculate in __init__()?
:param node_hostname: Hostname of the node which has the web browser.
:type node_hostname: str
:param sticky: If True, calculate the reward based on the most recent response status. If False, only calculate
the reward if there were any responses this timestep.
:type sticky: bool
"""
self._node: str = node_hostname
self.location_in_state: List[str] = ["network", "nodes", node_hostname, "applications", "WebBrowser"]
self.sticky: bool = sticky
self.reward: float = 0.0
"""Reward value calculated last time any responses were seen. Used for persisting sticky rewards."""
class ConfigSchema(AbstractReward.ConfigSchema):
"""ConfigSchema for WebpageUnavailablePenalty."""
type: str = "WEBPAGE_UNAVAILABLE_PENALTY"
node_hostname: str = ""
sticky: bool = True
def calculate(self, state: Dict, last_action_response: "AgentHistoryItem") -> float:
"""
@@ -274,6 +241,13 @@ class WebpageUnavailablePenalty(AbstractReward):
:return: Reward value
:rtype: float
"""
self.location_in_state = [
"network",
"nodes",
self.config.node_hostname,
"applications",
"WebBrowser",
]
web_browser_state = access_from_nested_dict(state, self.location_in_state)
if web_browser_state is NOT_PRESENT_IN_STATE:
@@ -283,14 +257,14 @@ class WebpageUnavailablePenalty(AbstractReward):
request_attempted = last_action_response.request == [
"network",
"node",
self._node,
self.config.node_hostname,
"application",
"WebBrowser",
"execute",
]
# skip calculating if sticky and no new codes, reusing last step value
if not request_attempted and self.sticky:
if not request_attempted and self.config.sticky:
return self.reward
if last_action_response.response.status != "success":
@@ -298,7 +272,7 @@ class WebpageUnavailablePenalty(AbstractReward):
elif web_browser_state is NOT_PRESENT_IN_STATE or not web_browser_state["history"]:
_LOGGER.debug(
"Web browser reward could not be calculated because the web browser history on node",
f"{self._node} was not reported in the simulation state. Returning 0.0",
f"{self.config.node_hostname} was not reported in the simulation state. Returning 0.0",
)
self.reward = 0.0
else:
@@ -312,37 +286,19 @@ class WebpageUnavailablePenalty(AbstractReward):
return self.reward
@classmethod
def from_config(cls, config: dict) -> AbstractReward:
"""
Build the reward component object from config.
:param config: Configuration dictionary.
:type config: Dict
"""
node_hostname = config.get("node_hostname")
sticky = config.get("sticky", True)
return cls(node_hostname=node_hostname, sticky=sticky)
class GreenAdminDatabaseUnreachablePenalty(AbstractReward):
class GreenAdminDatabaseUnreachablePenalty(AbstractReward, identifier="GREEN_ADMIN_DATABASE_UNREACHABLE_PENALTY"):
"""Penalises the agent when the green db clients fail to connect to the database."""
def __init__(self, node_hostname: str, sticky: bool = True) -> None:
"""
Initialise the reward component.
config: "GreenAdminDatabaseUnreachablePenalty.ConfigSchema"
reward: float = 0.0
:param node_hostname: Hostname of the node where the database client sits.
:type node_hostname: str
:param sticky: If True, calculate the reward based on the most recent response status. If False, only calculate
the reward if there were any responses this timestep.
:type sticky: bool
"""
self._node: str = node_hostname
self.location_in_state: List[str] = ["network", "nodes", node_hostname, "applications", "DatabaseClient"]
self.sticky: bool = sticky
self.reward: float = 0.0
"""Reward value calculated last time any responses were seen. Used for persisting sticky rewards."""
class ConfigSchema(AbstractReward.ConfigSchema):
"""ConfigSchema for GreenAdminDatabaseUnreachablePenalty."""
type: str = "GREEN_ADMIN_DATABASE_UNREACHABLE_PENALTY"
node_hostname: str
sticky: bool = True
def calculate(self, state: Dict, last_action_response: "AgentHistoryItem") -> float:
"""
@@ -362,7 +318,7 @@ class GreenAdminDatabaseUnreachablePenalty(AbstractReward):
request_attempted = last_action_response.request == [
"network",
"node",
self._node,
self.config.node_hostname,
"application",
"DatabaseClient",
"execute",
@@ -371,7 +327,7 @@ class GreenAdminDatabaseUnreachablePenalty(AbstractReward):
if request_attempted: # if agent makes request, always recalculate fresh value
last_action_response.reward_info = {"connection_attempt_status": last_action_response.response.status}
self.reward = 1.0 if last_action_response.response.status == "success" else -1.0
elif not self.sticky: # if no new request and not sticky, set reward to 0
elif not self.config.sticky: # if no new request and not sticky, set reward to 0
last_action_response.reward_info = {"connection_attempt_status": "n/a"}
self.reward = 0.0
else: # if no new request and sticky, reuse reward value from last step
@@ -380,47 +336,30 @@ class GreenAdminDatabaseUnreachablePenalty(AbstractReward):
return self.reward
@classmethod
def from_config(cls, config: Dict) -> AbstractReward:
"""
Build the reward component object from config.
:param config: Configuration dictionary.
:type config: Dict
"""
node_hostname = config.get("node_hostname")
sticky = config.get("sticky", True)
return cls(node_hostname=node_hostname, sticky=sticky)
class SharedReward(AbstractReward):
class SharedReward(AbstractReward, identifier="SHARED_REWARD"):
"""Adds another agent's reward to the overall reward."""
def __init__(self, agent_name: Optional[str] = None) -> None:
config: "SharedReward.ConfigSchema"
class ConfigSchema(AbstractReward.ConfigSchema):
"""Config schema for SharedReward."""
type: str = "SHARED_REWARD"
agent_name: str
def default_callback(agent_name: str) -> Never:
"""
Initialise the shared reward.
Default callback to prevent calling this reward until it's properly initialised.
The agent_name is a placeholder value. It starts off as none, but it must be set before this reward can work
correctly.
:param agent_name: The name whose reward is an input
:type agent_name: Optional[str]
SharedReward should not be used until the game layer replaces self.callback with a reference to the
function that retrieves the desired agent's reward. Therefore, we define this default callback that raises
an error.
"""
self.agent_name = agent_name
"""Agent whose reward to track."""
raise RuntimeError("Attempted to calculate SharedReward but it was not initialised properly.")
def default_callback(agent_name: str) -> Never:
"""
Default callback to prevent calling this reward until it's properly initialised.
SharedReward should not be used until the game layer replaces self.callback with a reference to the
function that retrieves the desired agent's reward. Therefore, we define this default callback that raises
an error.
"""
raise RuntimeError("Attempted to calculate SharedReward but it was not initialised properly.")
self.callback: Callable[[str], float] = default_callback
"""Method that retrieves an agent's current reward given the agent's name."""
callback: Callable[[str], float] = default_callback
"""Method that retrieves an agent's current reward given the agent's name."""
def calculate(self, state: Dict, last_action_response: "AgentHistoryItem") -> float:
"""Simply access the other agent's reward and return it.
@@ -432,36 +371,24 @@ class SharedReward(AbstractReward):
:return: Reward value
:rtype: float
"""
return self.callback(self.agent_name)
@classmethod
def from_config(cls, config: Dict) -> "SharedReward":
"""
Build the SharedReward object from config.
:param config: Configuration dictionary
:type config: Dict
"""
agent_name = config.get("agent_name")
return cls(agent_name=agent_name)
return self.callback(self.config.agent_name)
class ActionPenalty(AbstractReward):
"""Apply a negative reward when taking any action except do_nothing."""
class ActionPenalty(AbstractReward, identifier="ACTION_PENALTY"):
"""Apply a negative reward when taking any action except DONOTHING."""
def __init__(self, action_penalty: float, do_nothing_penalty: float) -> None:
"""
Initialise the reward.
Reward or penalise agents for doing nothing or taking actions.
config: "ActionPenalty.ConfigSchema"
class ConfigSchema(AbstractReward.ConfigSchema):
"""Config schema for ActionPenalty.
:param action_penalty: Reward to give agents for taking any action except do_nothing
:type action_penalty: float
:param do_nothing_penalty: Reward to give agent for taking the do_nothing action
:type do_nothing_penalty: float
"""
self.action_penalty = action_penalty
self.do_nothing_penalty = do_nothing_penalty
action_penalty: float = -1.0
do_nothing_penalty: float = 0.0
def calculate(self, state: Dict, last_action_response: "AgentHistoryItem") -> float:
"""Calculate the penalty to be applied.
@@ -475,31 +402,14 @@ class ActionPenalty(AbstractReward):
"""
if last_action_response.action == "do_nothing":
return self.do_nothing_penalty
else:
return self.action_penalty
@classmethod
def from_config(cls, config: Dict) -> "ActionPenalty":
"""Build the ActionPenalty object from config."""
action_penalty = config.get("action_penalty", -1.0)
do_nothing_penalty = config.get("do_nothing_penalty", 0.0)
return cls(action_penalty=action_penalty, do_nothing_penalty=do_nothing_penalty)
else:
return self.config.action_penalty
class RewardFunction:
"""Manages the reward function for the agent."""
rew_class_identifiers: Dict[str, Type[AbstractReward]] = {
"DUMMY": DummyReward,
"DATABASE_FILE_INTEGRITY": DatabaseFileIntegrity,
"WEB_SERVER_404_PENALTY": WebServer404Penalty,
"WEBPAGE_UNAVAILABLE_PENALTY": WebpageUnavailablePenalty,
"GREEN_ADMIN_DATABASE_UNREACHABLE_PENALTY": GreenAdminDatabaseUnreachablePenalty,
"SHARED_REWARD": SharedReward,
"ACTION_PENALTY": ActionPenalty,
}
"""List of reward class identifiers."""
def __init__(self):
"""Initialise the reward function object."""
self.reward_components: List[Tuple[AbstractReward, float]] = []
@@ -534,7 +444,7 @@ class RewardFunction:
@classmethod
def from_config(cls, config: Dict) -> "RewardFunction":
"""Create a reward function from a config dictionary.
"""Create a reward function from a config dictionary and its related reward class.
:param config: dict of options for the reward manager's constructor
:type config: Dict
@@ -545,8 +455,11 @@ class RewardFunction:
for rew_component_cfg in config["reward_components"]:
rew_type = rew_component_cfg["type"]
# XXX: If options key is missing add key then add type key.
if "options" not in rew_component_cfg:
rew_component_cfg["options"] = {}
rew_component_cfg["options"]["type"] = rew_type
weight = rew_component_cfg.get("weight", 1.0)
rew_class = cls.rew_class_identifiers[rew_type]
rew_instance = rew_class.from_config(config=rew_component_cfg.get("options", {}))
rew_instance = AbstractReward.from_config(rew_component_cfg["options"])
new.register_component(component=rew_instance, weight=weight)
return new

2
src/primaite/game/agent/scripted_agents/__init__.py
View File

@@ -1 +1 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK

2
src/primaite/game/agent/scripted_agents/data_manipulation_bot.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
import random
from typing import Dict, Tuple

2
src/primaite/game/agent/scripted_agents/probabilistic_agent.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
"""Agents with predefined behaviours."""
from typing import Dict, Optional, Tuple

2
src/primaite/game/agent/scripted_agents/random_agent.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
import random
from typing import Dict, Optional, Tuple

2
src/primaite/game/agent/scripted_agents/tap001.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
import random
from typing import Dict, Tuple

2
src/primaite/game/agent/utils.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
from typing import Any, Dict, Hashable, Optional, Sequence
NOT_PRESENT_IN_STATE = object()

6
src/primaite/game/game.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
"""PrimAITE game - Encapsulates the simulation and agents."""
from ipaddress import IPv4Address
from typing import Dict, List, Optional, Union
@@ -376,7 +376,7 @@ class PrimaiteGame:
if service_class is not None:
_LOGGER.debug(f"installing {service_type} on node {new_node.hostname}")
new_node.software_manager.install(service_class)
new_node.software_manager.install(service_class, **service_cfg.get("options", {}))
new_service = new_node.software_manager.software[service_class.__name__]
# fixing duration for the service
@@ -629,7 +629,7 @@ class PrimaiteGame:
for comp, weight in agent.reward_function.reward_components:
if isinstance(comp, SharedReward):
comp: SharedReward
graph[name].add(comp.agent_name)
graph[name].add(comp.config.agent_name)
# while constructing the graph, we might as well set up the reward sharing itself.
comp.callback = lambda agent_name: self.agents[agent_name].reward_function.current_reward

2
src/primaite/game/science.py
View File

@@ -1,4 +1,4 @@
# © Crown-owned copyright 2024, Defence Science and Technology Laboratory UK
# © Crown-owned copyright 2025, Defence Science and Technology Laboratory UK
from random import random
from typing import Any, Iterable, Mapping