{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 0.638860285282135, "min": 0.5963925719261169, "max": 1.7856649160385132, "count": 200 }, "Agent.Policy.Entropy.sum": { "value": 9582.904296875, "min": 8945.888671875, "max": 26833.1875, "count": 200 }, "Agent.Environment.EpisodeLength.mean": { "value": 999.0, "min": 35.02877697841727, "max": 999.0, "count": 200 }, "Agent.Environment.EpisodeLength.sum": { "value": 14985.0, "min": 12471.0, "max": 17250.0, "count": 200 }, "Agent.OceanPlasticCollector.GlobalReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "Agent.OceanPlasticCollector.GlobalReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "Agent.OceanPlasticCollector.LocalReward.mean": { "value": -5.866666666666666, "min": -49.470588235294116, "max": -1.4666666666666666, "count": 200 }, "Agent.OceanPlasticCollector.LocalReward.sum": { "value": -88.0, "min": -8778.0, "max": -22.0, "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": 2999415.0, "min": 14957.0, "max": 2999415.0, "count": 200 }, "Agent.Step.sum": { "value": 2999415.0, "min": 14957.0, "max": 2999415.0, "count": 200 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": 0.1154472753405571, "min": -0.8862332105636597, "max": 1.0572350025177002, "count": 200 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 1.7317091226577759, "min": -324.3613586425781, "max": 37.66022872924805, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": -0.2670222520828247, "min": -29.950918197631836, "max": -0.004970827605575323, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": -4.00533390045166, "min": -6228.71728515625, "max": -0.07456241548061371, "count": 200 }, "Agent.Environment.CumulativeReward.mean": { "value": -2.533333333333333, "min": -80.0, "max": -0.6666666666666666, "count": 200 }, "Agent.Environment.CumulativeReward.sum": { "value": -38.0, "min": -21398.0, "max": -10.0, "count": 200 }, "Agent.Policy.CuriosityReward.mean": { "value": 1.0025015552838643, "min": 0.05217977417991138, "max": 8.019394622129553, "count": 200 }, "Agent.Policy.CuriosityReward.sum": { "value": 15.037523329257965, "min": 14.887594163417816, "max": 308.0722427070141, "count": 200 }, "Agent.Policy.ExtrinsicReward.mean": { "value": -2.2799999793370564, "min": -71.99999934205643, "max": -0.599999976158142, "count": 200 }, "Agent.Policy.ExtrinsicReward.sum": { "value": -34.19999969005585, "min": -19258.199901223183, "max": -8.999999642372131, "count": 200 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.02782441684129563, "min": 0.017161196083620642, "max": 0.03423922988727237, "count": 200 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.02782441684129563, "min": 0.017161196083620642, "max": 0.05935260948414604, "count": 200 }, "Agent.Losses.ValueLoss.mean": { "value": 0.008881246953299551, "min": 0.0037338478864650383, "max": 319.1523635864258, "count": 200 }, "Agent.Losses.ValueLoss.sum": { "value": 0.008881246953299551, "min": 0.003950864584608512, "max": 319.1523635864258, "count": 200 }, "Agent.Policy.LearningRate.mean": { "value": 6.58599780499984e-07, "min": 6.58599780499984e-07, "max": 0.00029895630034790005, "count": 200 }, "Agent.Policy.LearningRate.sum": { "value": 6.58599780499984e-07, "min": 6.58599780499984e-07, "max": 0.0005927730024089999, "count": 200 }, "Agent.Policy.Epsilon.mean": { "value": 0.1002195, "min": 0.1002195, "max": 0.19965209999999994, "count": 200 }, "Agent.Policy.Epsilon.sum": { "value": 0.1002195, "min": 0.1002195, "max": 0.397591, "count": 200 }, "Agent.Policy.Beta.mean": { "value": 2.0953049999999737e-05, "min": 2.0953049999999737e-05, "max": 0.004982639789999998, "count": 200 }, "Agent.Policy.Beta.sum": { "value": 2.0953049999999737e-05, "min": 2.0953049999999737e-05, "max": 0.009879790900000001, "count": 200 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.00850866102811062, "min": 0.00850866102811062, "max": 0.1835723704348008, "count": 200 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.00850866102811062, "min": 0.00850866102811062, "max": 0.3432569647828738, "count": 200 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 0.023177117701958527, "min": 0.015754404731772163, "max": 1.791323447227478, "count": 200 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 0.023177117701958527, "min": 0.015754404731772163, "max": 3.0221930185953774, "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": "1716543922", "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_3_run_id_2_train.yaml --run-id=OceanPlasticCollection/train/OceanPlasticCollection_task_3_run_id_2_train --base-port 5008", "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": "1716566114" }, "total": 22192.4904069, "count": 1, "self": 0.318027000001166, "children": { "run_training.setup": { "total": 0.06495130000000005, "count": 1, "self": 0.06495130000000005 }, "TrainerController.start_learning": { "total": 22192.1074286, "count": 1, "self": 21.209973600354715, "children": { "TrainerController._reset_env": { "total": 3.4096910000000005, "count": 1, "self": 3.4096910000000005 }, "TrainerController.advance": { "total": 22167.311599399643, "count": 1002092, "self": 17.492362600998604, "children": { "env_step": { "total": 22149.819236798645, "count": 1002092, "self": 15230.504854698298, "children": { "SubprocessEnvManager._take_step": { "total": 6908.2548703012235, "count": 1002092, "self": 33.19558060192776, "children": { "TorchPolicy.evaluate": { "total": 6875.059289699296, "count": 1000812, "self": 6875.059289699296 } } }, "workers": { "total": 11.059511799122475, "count": 1002092, "self": 0.0, "children": { "worker_root": { "total": 22170.132985800516, "count": 1002092, "is_parallel": true, "self": 7618.560021900639, "children": { "steps_from_proto": { "total": 0.00045319999999993144, "count": 1, "is_parallel": true, "self": 0.00011169999999927072, "children": { "_process_maybe_compressed_observation": { "total": 0.00024240000000030903, "count": 2, "is_parallel": true, "self": 3.940000000035582e-05, "children": { "_observation_to_np_array": { "total": 0.00020299999999995322, "count": 3, "is_parallel": true, "self": 0.00020299999999995322 } } }, "_process_rank_one_or_two_observation": { "total": 9.910000000035168e-05, "count": 2, "is_parallel": true, "self": 9.910000000035168e-05 } } }, "UnityEnvironment.step": { "total": 14551.572510699876, "count": 1002092, "is_parallel": true, "self": 103.03187409963903, "children": { "UnityEnvironment._generate_step_input": { "total": 48.80345220193814, "count": 1002092, "is_parallel": true, "self": 48.80345220193814 }, "communicator.exchange": { "total": 13998.13538649917, "count": 1002092, "is_parallel": true, "self": 13998.13538649917 }, "steps_from_proto": { "total": 401.6017978991271, "count": 1002092, "is_parallel": true, "self": 94.54391369873741, "children": { "_process_maybe_compressed_observation": { "total": 249.4358898001422, "count": 2004184, "is_parallel": true, "self": 36.148945999513614, "children": { "_observation_to_np_array": { "total": 213.2869438006286, "count": 3006915, "is_parallel": true, "self": 213.2869438006286 } } }, "_process_rank_one_or_two_observation": { "total": 57.6219944002475, "count": 2004184, "is_parallel": true, "self": 57.6219944002475 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.9800001357216388e-05, "count": 1, "self": 2.9800001357216388e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 22175.768426198414, "count": 1225061, "is_parallel": true, "self": 35.48868049718294, "children": { "process_trajectory": { "total": 19568.239440801226, "count": 1225061, "is_parallel": true, "self": 19567.020813601226, "children": { "RLTrainer._checkpoint": { "total": 1.218627200001265, "count": 6, "is_parallel": true, "self": 1.218627200001265 } } }, "_update_policy": { "total": 2572.040304900006, "count": 251, "is_parallel": true, "self": 1769.8831837001612, "children": { "TorchPPOOptimizer.update": { "total": 802.1571211998448, "count": 8253, "is_parallel": true, "self": 802.1571211998448 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1761347999999998, "count": 1, "self": 0.012050100001943065, "children": { "RLTrainer._checkpoint": { "total": 0.16408469999805675, "count": 1, "self": 0.16408469999805675 } } } } } } }