{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 3.9668312072753906, "min": 3.7804253101348877, "max": 4.380436420440674, "count": 100 }, "Agent.Policy.Entropy.sum": { "value": 19457.306640625, "min": 5902.4345703125, "max": 31717.58203125, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.mean": { "value": 0.8925926861939607, "min": 0.5805555743475755, "max": 0.9000000953674316, "count": 100 }, "Agent.WildfireResourceManagement.IndividualResourceCount.sum": { "value": 24.10000252723694, "min": 7.600000739097595, "max": 40.000004172325134, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.mean": { "value": 2.1979813239088766, "min": 0.3762214953016433, "max": 12.163262406984964, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoNeighbours.sum": { "value": 59.345495745539665, "min": 3.3859934577147897, "max": 366.9930374722462, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.mean": { "value": 195.94763296621818, "min": 45.09299181732867, "max": 500.01685587565106, "count": 100 }, "Agent.WildfireResourceManagement.RewardforMovingResourcestoSelf.sum": { "value": 5290.586090087891, "min": 1623.347705423832, "max": 8641.529499053955, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.mean": { "value": 46.293033599853516, "min": 25.176106135050457, "max": 117.2500237358941, "count": 100 }, "Agent.WildfireResourceManagement.CollectivePerformance.sum": { "value": 1249.911907196045, "min": 448.02629470825195, "max": 2048.968963623047, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.mean": { "value": 23.532668590545654, "min": 13.759139292769962, "max": 58.621494717068146, "count": 100 }, "Agent.WildfireResourceManagement.IndividualPerformance.sum": { "value": 635.3820519447327, "min": 211.78832626342773, "max": 1010.5693788528442, "count": 100 }, "Agent.Environment.LessonNumber.difficulty.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "Agent.Environment.LessonNumber.difficulty.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "Agent.Environment.LessonNumber.task.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "Agent.Environment.LessonNumber.task.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "Agent.Environment.EpisodeLength.mean": { "value": 181.66666666666666, "min": 96.33333333333333, "max": 473.0, "count": 100 }, "Agent.Environment.EpisodeLength.sum": { "value": 4905.0, "min": 1512.0, "max": 7803.0, "count": 100 }, "Agent.Step.mean": { "value": 449977.0, "min": 4405.0, "max": 449977.0, "count": 100 }, "Agent.Step.sum": { "value": 449977.0, "min": 4405.0, "max": 449977.0, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": 0.00578606640920043, "min": -0.045637745410203934, "max": 0.09990525245666504, "count": 100 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 0.11572133004665375, "min": -0.8686326742172241, "max": 2.7380776405334473, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 89.14933776855469, "min": 3.151017189025879, "max": 131.51524353027344, "count": 100 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 1782.98681640625, "min": 81.92644500732422, "max": 4076.97265625, "count": 100 }, "Agent.Environment.CumulativeReward.mean": { "value": 321.5479022026062, "min": 96.69844296039679, "max": 614.6264218417081, "count": 100 }, "Agent.Environment.CumulativeReward.sum": { "value": 6430.958044052124, "min": 2918.829081296921, "max": 8660.427490234375, "count": 100 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.03222924910951406, "min": 0.014380116129102997, "max": 0.26607194998198086, "count": 100 }, "Agent.Policy.CuriosityReward.sum": { "value": 0.6445849821902812, "min": 0.48400826193392277, "max": 5.135645776987076, "count": 100 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 321.5479022026062, "min": 96.69844296039679, "max": 614.6264218417081, "count": 100 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 6430.958044052124, "min": 2918.829081296921, "max": 8660.427490234375, "count": 100 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.06731047691286993, "min": 0.053174213441606194, "max": 0.08211484194571297, "count": 99 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.13462095382573985, "min": 0.053174213441606194, "max": 0.16422968389142595, "count": 99 }, "Agent.Losses.ValueLoss.mean": { "value": 787.9369762449553, "min": 100.27956397860657, "max": 1110.4575428903838, "count": 99 }, "Agent.Losses.ValueLoss.sum": { "value": 1575.8739524899106, "min": 100.27956397860657, "max": 2220.9150857807676, "count": 99 }, "Agent.Policy.LearningRate.mean": { "value": 1.4610995129999955e-06, "min": 1.4610995129999955e-06, "max": 0.00029848200050600006, "count": 99 }, "Agent.Policy.LearningRate.sum": { "value": 2.922199025999991e-06, "min": 2.922199025999991e-06, "max": 0.0005858280047239997, "count": 99 }, "Agent.Policy.Epsilon.mean": { "value": 0.10048699999999999, "min": 0.10048699999999999, "max": 0.199494, "count": 99 }, "Agent.Policy.Epsilon.sum": { "value": 0.20097399999999999, "min": 0.101576, "max": 0.3952760000000001, "count": 99 }, "Agent.Policy.Beta.mean": { "value": 5.865129999999986e-05, "min": 5.865129999999986e-05, "max": 0.009949450600000001, "count": 99 }, "Agent.Policy.Beta.sum": { "value": 0.00011730259999999973, "min": 0.00011730259999999973, "max": 0.0195280724, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.0059364226382802535, "min": 0.004110809447916431, "max": 0.4862046896242628, "count": 99 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.011872845276560507, "min": 0.004110809447916431, "max": 0.4862046896242628, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 3.808633321162426, "min": 3.682709720399645, "max": 4.390673973981072, "count": 99 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 7.617266642324852, "min": 3.682709720399645, "max": 8.669611559973823, "count": 99 }, "Agent.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Agent.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716645566", "python_version": "3.9.18 (main, Sep 11 2023, 14:09:26) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\pdsie\\anaconda3\\envs\\mlagents20\\Scripts\\mlagents-learn c:/users/pdsie/documents/hivex/src/hivex/training/baseline/ml_agents/configs/mlagents/tmp/train/WildfireResourceManagement_difficulty_3_task_1_run_id_0_train.yaml --run-id=WildfireResourceManagement/train/WildfireResourceManagement_difficulty_3_task_1_run_id_0_train --base-port 5006", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.7.1+cu110", "numpy_version": "1.21.0", "end_time_seconds": "1716647330" }, "total": 1763.6787115, "count": 1, "self": 0.18825479999986783, "children": { "run_training.setup": { "total": 0.049356999999999984, "count": 1, "self": 0.049356999999999984 }, "TrainerController.start_learning": { "total": 1763.4410997, "count": 1, "self": 1.1662981999820659, "children": { "TrainerController._reset_env": { "total": 2.1075382, "count": 1, "self": 2.1075382 }, "TrainerController.advance": { "total": 1760.0768772000179, "count": 50074, "self": 1.137395200033552, "children": { "env_step": { "total": 1758.9394819999843, "count": 50074, "self": 1476.5500912999805, "children": { "SubprocessEnvManager._take_step": { "total": 281.8926474000154, "count": 50074, "self": 1.9207899000046496, "children": { "TorchPolicy.evaluate": { "total": 279.97185750001074, "count": 50074, "self": 279.97185750001074 } } }, "workers": { "total": 0.49674329998837274, "count": 50074, "self": 0.0, "children": { "worker_root": { "total": 1760.8244052999887, "count": 50074, "is_parallel": true, "self": 346.75208069998916, "children": { "steps_from_proto": { "total": 0.00026729999999997034, "count": 1, "is_parallel": true, "self": 0.00012269999999969805, "children": { "_process_rank_one_or_two_observation": { "total": 0.0001446000000002723, "count": 2, "is_parallel": true, "self": 0.0001446000000002723 } } }, "UnityEnvironment.step": { "total": 1414.0720572999996, "count": 50074, "is_parallel": true, "self": 3.771616100005076, "children": { "UnityEnvironment._generate_step_input": { "total": 4.718567200012059, "count": 50074, "is_parallel": true, "self": 4.718567200012059 }, "communicator.exchange": { "total": 1394.9378351999794, "count": 50074, "is_parallel": true, "self": 1394.9378351999794 }, "steps_from_proto": { "total": 10.644038800003129, "count": 50074, "is_parallel": true, "self": 5.410248600030676, "children": { "_process_rank_one_or_two_observation": { "total": 5.233790199972453, "count": 100148, "is_parallel": true, "self": 5.233790199972453 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.130000007127819e-05, "count": 1, "self": 2.130000007127819e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1760.1467308999916, "count": 87516, "is_parallel": true, "self": 3.1565607999880285, "children": { "process_trajectory": { "total": 1389.8533329000027, "count": 87516, "is_parallel": true, "self": 1389.8533329000027 }, "_update_policy": { "total": 367.13683720000097, "count": 141, "is_parallel": true, "self": 180.21210090000932, "children": { "TorchPPOOptimizer.update": { "total": 186.92473629999165, "count": 10335, "is_parallel": true, "self": 186.92473629999165 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09036480000008851, "count": 1, "self": 0.006183100000043851, "children": { "RLTrainer._checkpoint": { "total": 0.08418170000004466, "count": 1, "self": 0.08418170000004466 } } } } } } }