{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 0.4797113835811615, "min": 0.45411908626556396, "max": 1.787257194519043, "count": 200 }, "Agent.Policy.Entropy.sum": { "value": 7199.98828125, "min": 6708.490234375, "max": 27988.41796875, "count": 200 }, "Agent.Environment.EpisodeLength.mean": { "value": 160.4516129032258, "min": 35.11267605633803, "max": 459.75, "count": 200 }, "Agent.Environment.EpisodeLength.sum": { "value": 14922.0, "min": 12228.0, "max": 17409.0, "count": 200 }, "Agent.OceanPlasticCollector.GlobalReward.mean": { "value": 270.95790404510785, "min": 1.317898467965964, "max": 604.9524826845039, "count": 200 }, "Agent.OceanPlasticCollector.GlobalReward.sum": { "value": 48772.42272811942, "min": 545.6099657379091, "max": 70420.84932395071, "count": 200 }, "Agent.OceanPlasticCollector.LocalReward.mean": { "value": 149.92222222222222, "min": 17.652173913043477, "max": 270.4691358024691, "count": 200 }, "Agent.OceanPlasticCollector.LocalReward.sum": { "value": 26986.0, "min": 7308.0, "max": 34817.0, "count": 200 }, "Agent.Environment.LessonNumber.task.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "Agent.Environment.LessonNumber.task.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "Agent.Step.mean": { "value": 2999817.0, "min": 14967.0, "max": 2999817.0, "count": 200 }, "Agent.Step.sum": { "value": 2999817.0, "min": 14967.0, "max": 2999817.0, "count": 200 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": 0.16175217926502228, "min": 0.05323157459497452, "max": 1.155686855316162, "count": 200 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 14.881200790405273, "min": 5.788083076477051, "max": 144.9110107421875, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 310.5462341308594, "min": -7.7407145500183105, "max": 342.80511474609375, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 28570.25390625, "min": -2833.1015625, "max": 45206.015625, "count": 200 }, "Agent.Environment.CumulativeReward.mean": { "value": 766.547702750434, "min": -14.746666854222616, "max": 1526.9491478341524, "count": 200 }, "Agent.Environment.CumulativeReward.sum": { "value": 70522.38865303993, "min": -5869.800079584122, "max": 95523.3875041008, "count": 200 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.2542370162985247, "min": 0.049774529879150944, "max": 3.4712647386625703, "count": 200 }, "Agent.Policy.CuriosityReward.sum": { "value": 23.389805499464273, "min": 21.05462613888085, "max": 252.74574196711183, "count": 200 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 689.8929111607697, "min": -13.272000325361887, "max": 1374.2541994931269, "count": 200 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 63470.14782679081, "min": -5282.820174634457, "max": 85971.04710793495, "count": 200 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.022255855907375614, "min": 0.017184668856983384, "max": 0.03254731826794644, "count": 200 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.04451171181475123, "min": 0.017184668856983384, "max": 0.05788607834415002, "count": 200 }, "Agent.Losses.ValueLoss.mean": { "value": 3797.5549438476564, "min": 169.91888580322265, "max": 6523.48544921875, "count": 200 }, "Agent.Losses.ValueLoss.sum": { "value": 7595.109887695313, "min": 169.91888580322265, "max": 13043.020198567709, "count": 200 }, "Agent.Policy.LearningRate.mean": { "value": 8.820997059999996e-07, "min": 8.820997059999996e-07, "max": 0.00029895630034790005, "count": 200 }, "Agent.Policy.LearningRate.sum": { "value": 1.7641994119999991e-06, "min": 1.7641994119999991e-06, "max": 0.0005927097024301001, "count": 200 }, "Agent.Policy.Epsilon.mean": { "value": 0.10029399999999998, "min": 0.10029399999999998, "max": 0.19965209999999994, "count": 200 }, "Agent.Policy.Epsilon.sum": { "value": 0.20058799999999996, "min": 0.10082360000000001, "max": 0.3975699, "count": 200 }, "Agent.Policy.Beta.mean": { "value": 2.4670599999999994e-05, "min": 2.4670599999999994e-05, "max": 0.004982639789999998, "count": 200 }, "Agent.Policy.Beta.sum": { "value": 4.934119999999999e-05, "min": 4.934119999999999e-05, "max": 0.009878738010000002, "count": 200 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.014932409487664701, "min": 0.01433597697565953, "max": 0.18357288849850495, "count": 200 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.029864818975329402, "min": 0.01433597697565953, "max": 0.3334345837434133, "count": 200 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 0.11149372160434723, "min": 0.10612237801154455, "max": 1.791323435306549, "count": 200 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 0.22298744320869446, "min": 0.10612237801154455, "max": 3.092707387606303, "count": 200 }, "Agent.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "Agent.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716242423", "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/OceanPlasticCollection_task_0_run_id_0_train.yaml --run-id=OceanPlasticCollection/train/OceanPlasticCollection_task_0_run_id_0_train --base-port 5007", "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": "1.21.2", "end_time_seconds": "1716271199" }, "total": 28777.320956, "count": 1, "self": 0.7713683000001765, "children": { "run_training.setup": { "total": 0.05752600000000008, "count": 1, "self": 0.05752600000000008 }, "TrainerController.start_learning": { "total": 28776.4920617, "count": 1, "self": 26.192018400066445, "children": { "TrainerController._reset_env": { "total": 2.2604235, "count": 1, "self": 2.2604235 }, "TrainerController.advance": { "total": 28747.843563499933, "count": 1005085, "self": 23.23895510065995, "children": { "env_step": { "total": 28724.604608399273, "count": 1005085, "self": 19329.767481399856, "children": { "SubprocessEnvManager._take_step": { "total": 9380.061038300126, "count": 1005085, "self": 45.210927699550666, "children": { "TorchPolicy.evaluate": { "total": 9334.850110600575, "count": 1000075, "self": 9334.850110600575 } } }, "workers": { "total": 14.776088699291243, "count": 1005085, "self": 0.0, "children": { "worker_root": { "total": 28750.051403901714, "count": 1005085, "is_parallel": true, "self": 10340.105120100667, "children": { "steps_from_proto": { "total": 0.0004262999999999906, "count": 1, "is_parallel": true, "self": 0.00011119999999964492, "children": { "_process_maybe_compressed_observation": { "total": 0.00022990000000011612, "count": 2, "is_parallel": true, "self": 3.160000000046459e-05, "children": { "_observation_to_np_array": { "total": 0.00019829999999965153, "count": 3, "is_parallel": true, "self": 0.00019829999999965153 } } }, "_process_rank_one_or_two_observation": { "total": 8.520000000022954e-05, "count": 2, "is_parallel": true, "self": 8.520000000022954e-05 } } }, "UnityEnvironment.step": { "total": 18409.945857501047, "count": 1005085, "is_parallel": true, "self": 139.23127399751684, "children": { "UnityEnvironment._generate_step_input": { "total": 66.17219810147604, "count": 1005085, "is_parallel": true, "self": 66.17219810147604 }, "communicator.exchange": { "total": 17701.456413700475, "count": 1005085, "is_parallel": true, "self": 17701.456413700475 }, "steps_from_proto": { "total": 503.08597170157975, "count": 1005085, "is_parallel": true, "self": 117.22940070002039, "children": { "_process_maybe_compressed_observation": { "total": 318.687236299181, "count": 2010170, "is_parallel": true, "self": 42.07804160099988, "children": { "_observation_to_np_array": { "total": 276.6091946981811, "count": 3019125, "is_parallel": true, "self": 276.6091946981811 } } }, "_process_rank_one_or_two_observation": { "total": 67.16933470237839, "count": 2010170, "is_parallel": true, "self": 67.16933470237839 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.029999763588421e-05, "count": 1, "self": 4.029999763588421e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 28754.307471097636, "count": 1536324, "is_parallel": true, "self": 54.24060769933203, "children": { "process_trajectory": { "total": 24413.15793489832, "count": 1536324, "is_parallel": true, "self": 24411.518989598317, "children": { "RLTrainer._checkpoint": { "total": 1.638945300004707, "count": 6, "is_parallel": true, "self": 1.638945300004707 } } }, "_update_policy": { "total": 4286.908928499984, "count": 278, "is_parallel": true, "self": 2880.6284980001737, "children": { "TorchPPOOptimizer.update": { "total": 1406.28043049981, "count": 8481, "is_parallel": true, "self": 1406.28043049981 } } } } } } } } }, "TrainerController._save_models": { "total": 0.19601600000169128, "count": 1, "self": 0.011950100000831299, "children": { "RLTrainer._checkpoint": { "total": 0.18406590000085998, "count": 1, "self": 0.18406590000085998 } } } } } } }