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

Merge remote-tracking branch 'origin/dev' into user-guide-feedback-core-fixes

Browse Source
This commit is contained in:
Archer.Bowen
2024-05-31 17:13:27 +01:00
parent 0ac57147cd 262390b74d
commit 93a729029c
28 changed files with 291 additions and 241 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/primaite/notebooks/Data-Manipulation-Customising-Red-Agent.ipynb
View File

@@ -22,7 +22,7 @@
"# Imports\n",
"\n",
"from primaite.config.load import data_manipulation_config_path\n",
"from primaite.game.agent.interface import AgentActionHistoryItem\n",
"from primaite.game.agent.interface import AgentHistoryItem\n",
"from primaite.session.environment import PrimaiteGymEnv\n",
"import yaml\n",
"from pprint import pprint"
@@ -63,7 +63,7 @@
"source": [
"def friendly_output_red_action(info):\n",
" # parse the info dict form step output and write out what the red agent is doing\n",
" red_info : AgentActionHistoryItem = info['agent_actions']['data_manipulation_attacker']\n",
" red_info : AgentHistoryItem = info['agent_actions']['data_manipulation_attacker']\n",
" red_action = red_info.action\n",
" if red_action == 'DONOTHING':\n",
" red_str = 'DO NOTHING'\n",

4
src/primaite/notebooks/Data-Manipulation-E2E-Demonstration.ipynb
View File

@@ -392,7 +392,7 @@
"# Imports\n",
"from primaite.config.load import data_manipulation_config_path\n",
"from primaite.session.environment import PrimaiteGymEnv\n",
"from primaite.game.agent.interface import AgentActionHistoryItem\n",
"from primaite.game.agent.interface import AgentHistoryItem\n",
"import yaml\n",
"from pprint import pprint\n"
]
@@ -444,7 +444,7 @@
"source": [
"def friendly_output_red_action(info):\n",
" # parse the info dict form step output and write out what the red agent is doing\n",
" red_info : AgentActionHistoryItem = info['agent_actions']['data_manipulation_attacker']\n",
" red_info : AgentHistoryItem = info['agent_actions']['data_manipulation_attacker']\n",
" red_action = red_info.action\n",
" if red_action == 'DONOTHING':\n",
" red_str = 'DO NOTHING'\n",

8
src/primaite/notebooks/Training-an-RLLIB-MARL-System.ipynb
View File

@@ -25,13 +25,13 @@
"from primaite.game.game import PrimaiteGame\n",
"import yaml\n",
"\n",
"from primaite.session.environment import PrimaiteRayEnv\n",
"from primaite.session.ray_envs import PrimaiteRayEnv\n",
"from primaite import PRIMAITE_PATHS\n",
"\n",
"import ray\n",
"from ray import air, tune\n",
"from ray.rllib.algorithms.ppo import PPOConfig\n",
"from primaite.session.environment import PrimaiteRayMARLEnv\n",
"from primaite.session.ray_envs import PrimaiteRayMARLEnv\n",
"\n",
"# If you get an error saying this config file doesn't exist, you may need to run `primaite setup` in your command line\n",
"# to copy the files to your user data path.\n",
@@ -60,8 +60,8 @@
" policies={'defender_1','defender_2'}, # These names are the same as the agents defined in the example config.\n",
" policy_mapping_fn=lambda agent_id, episode, worker, **kw: agent_id,\n",
" )\n",
" .environment(env=PrimaiteRayMARLEnv, env_config=cfg)#, disable_env_checking=True)\n",
" .rollouts(num_rollout_workers=0)\n",
" .environment(env=PrimaiteRayMARLEnv, env_config=cfg)\n",
" .env_runners(num_env_runners=0)\n",
" .training(train_batch_size=128)\n",
" )\n"
]

11
src/primaite/notebooks/Training-an-RLLib-Agent.ipynb
View File

@@ -18,8 +18,7 @@
"import yaml\n",
"from primaite.config.load import data_manipulation_config_path\n",
"\n",
"from primaite.session.environment import PrimaiteRayEnv\n",
"from ray.rllib.algorithms import ppo\n",
"from primaite.session.ray_envs import PrimaiteRayEnv\n",
"from ray import air, tune\n",
"import ray\n",
"from ray.rllib.algorithms.ppo import PPOConfig\n",
@@ -52,8 +51,8 @@
"\n",
"config = (\n",
" PPOConfig()\n",
" .environment(env=PrimaiteRayEnv, env_config=env_config, disable_env_checking=True)\n",
" .rollouts(num_rollout_workers=0)\n",
" .environment(env=PrimaiteRayEnv, env_config=env_config)\n",
" .env_runners(num_env_runners=0)\n",
" .training(train_batch_size=128)\n",
")\n"
]
@@ -74,7 +73,7 @@
"tune.Tuner(\n",
" \"PPO\",\n",
" run_config=air.RunConfig(\n",
" stop={\"timesteps_total\": 5 * 128}\n",
" stop={\"timesteps_total\": 512}\n",
" ),\n",
" param_space=config\n",
").fit()\n"
@@ -97,7 +96,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.11"
"version": "3.10.12"
}
},
"nbformat": 4,

7
src/primaite/notebooks/Training-an-SB3-Agent.ipynb
View File

@@ -43,7 +43,10 @@
"outputs": [],
"source": [
"with open(data_manipulation_config_path(), 'r') as f:\n",
" cfg = yaml.safe_load(f)"
" cfg = yaml.safe_load(f)\n",
"for agent in cfg['agents']:\n",
" if agent['ref'] == 'defender':\n",
" agent['agent_settings']['flatten_obs']=True"
]
},
{
@@ -177,7 +180,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.10"
"version": "3.10.12"
}
},
"nbformat": 4,

8
src/primaite/notebooks/Using-Episode-Schedules.ipynb
View File

@@ -254,8 +254,8 @@
"table = PrettyTable()\n",
"table.field_names = [\"step\", \"Green Action\", \"Red Action\"]\n",
"for i in range(21):\n",
" green_action = env.game.agents['green_A'].action_history[i].action\n",
" red_action = env.game.agents['red_A'].action_history[i].action\n",
" green_action = env.game.agents['green_A'].history[i].action\n",
" red_action = env.game.agents['red_A'].history[i].action\n",
" table.add_row([i, green_action, red_action])\n",
"print(table)"
]
@@ -285,8 +285,8 @@
"table = PrettyTable()\n",
"table.field_names = [\"step\", \"Green Action\", \"Red Action\"]\n",
"for i in range(21):\n",
" green_action = env.game.agents['green_B'].action_history[i].action\n",
" red_action = env.game.agents['red_B'].action_history[i].action\n",
" green_action = env.game.agents['green_B'].history[i].action\n",
" red_action = env.game.agents['red_B'].history[i].action\n",
" table.add_row([i, green_action, red_action])\n",
"print(table)"
]