{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 0.5306253433227539, "min": 0.49898743629455566, "max": 1.7881392240524292, "count": 200 }, "Agent.Policy.Entropy.sum": { "value": 7941.86962890625, "min": 6877.56591796875, "max": 26929.376953125, "count": 200 }, "Agent.Environment.EpisodeLength.mean": { "value": 183.85185185185185, "min": 35.369565217391305, "max": 577.7777777777778, "count": 200 }, "Agent.Environment.EpisodeLength.sum": { "value": 14892.0, "min": 12399.0, "max": 17439.0, "count": 200 }, "Agent.OceanPlasticCollector.GlobalReward.mean": { "value": 298.25300991119315, "min": 1.3685010688491916, "max": 562.4681555451618, "count": 200 }, "Agent.OceanPlasticCollector.GlobalReward.sum": { "value": 47422.22857587971, "min": 611.7199777755886, "max": 69435.68168136477, "count": 200 }, "Agent.OceanPlasticCollector.LocalReward.mean": { "value": 157.80503144654088, "min": 19.0917225950783, "max": 257.9375, "count": 200 }, "Agent.OceanPlasticCollector.LocalReward.sum": { "value": 25091.0, "min": 6873.0, "max": 33543.0, "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": 2999856.0, "min": 14995.0, "max": 2999856.0, "count": 200 }, "Agent.Step.sum": { "value": 2999856.0, "min": 14995.0, "max": 2999856.0, "count": 200 }, "Agent.Policy.CuriosityValueEstimate.mean": { "value": 0.27030399441719055, "min": -0.004683023318648338, "max": 1.2223944664001465, "count": 200 }, "Agent.Policy.CuriosityValueEstimate.sum": { "value": 21.894624710083008, "min": -1.2175860404968262, "max": 118.57225799560547, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 288.5648498535156, "min": -8.056370735168457, "max": 348.76446533203125, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 23373.75390625, "min": -2094.656494140625, "max": 41161.15625, "count": 200 }, "Agent.Environment.CumulativeReward.mean": { "value": 885.9131869269006, "min": -12.916335125571315, "max": 1451.7606051830535, "count": 200 }, "Agent.Environment.CumulativeReward.sum": { "value": 71758.96814107895, "min": -5321.530071735382, "max": 99525.08007621765, "count": 200 }, "Agent.Policy.CuriosityReward.mean": { "value": 0.30991002497619685, "min": 0.05206376354852058, "max": 8.034196149844389, "count": 200 }, "Agent.Policy.CuriosityReward.sum": { "value": 25.102712023071945, "min": 21.45027058199048, "max": 274.9943250827491, "count": 200 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 797.3218594009494, "min": -11.624701671519325, "max": 1306.5845138062823, "count": 200 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 64583.0706114769, "min": -4789.377088665962, "max": 89572.56913685799, "count": 200 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.022236945216233532, "min": 0.016801928527032335, "max": 0.032498174579814076, "count": 200 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.044473890432467064, "min": 0.016801928527032335, "max": 0.0605002747580522, "count": 200 }, "Agent.Losses.ValueLoss.mean": { "value": 3485.494217936198, "min": 126.44592258568966, "max": 6151.284423828125, "count": 200 }, "Agent.Losses.ValueLoss.sum": { "value": 6970.988435872396, "min": 126.62573547363282, "max": 10417.76612141927, "count": 200 }, "Agent.Policy.LearningRate.mean": { "value": 7.701997432999959e-07, "min": 7.701997432999959e-07, "max": 0.00029895630034790005, "count": 200 }, "Agent.Policy.LearningRate.sum": { "value": 1.5403994865999917e-06, "min": 1.5403994865999917e-06, "max": 0.0005927607024131001, "count": 200 }, "Agent.Policy.Epsilon.mean": { "value": 0.10025670000000002, "min": 0.10025670000000002, "max": 0.19965209999999994, "count": 200 }, "Agent.Policy.Epsilon.sum": { "value": 0.20051340000000004, "min": 0.10077589999999997, "max": 0.3975869000000001, "count": 200 }, "Agent.Policy.Beta.mean": { "value": 2.280932999999993e-05, "min": 2.280932999999993e-05, "max": 0.004982639789999998, "count": 200 }, "Agent.Policy.Beta.sum": { "value": 4.561865999999986e-05, "min": 4.561865999999986e-05, "max": 0.00987958631, "count": 200 }, "Agent.Losses.CuriosityForwardLoss.mean": { "value": 0.01628636669677993, "min": 0.015522598568350077, "max": 0.1835712509850661, "count": 200 }, "Agent.Losses.CuriosityForwardLoss.sum": { "value": 0.03257273339355986, "min": 0.015905051957815886, "max": 0.33890696118275326, "count": 200 }, "Agent.Losses.CuriosityInverseLoss.mean": { "value": 0.1593244475622972, "min": 0.12232522579530875, "max": 1.7913235346476237, "count": 200 }, "Agent.Losses.CuriosityInverseLoss.sum": { "value": 0.3186488951245944, "min": 0.12283845146497091, "max": 3.0615293025970463, "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": "1716785038", "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_2_run_id_1_train.yaml --run-id=OceanPlasticCollection/train/OceanPlasticCollection_task_2_run_id_1_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": "1716811251" }, "total": 26213.0630382, "count": 1, "self": 0.7105160000028263, "children": { "run_training.setup": { "total": 0.05819149999999995, "count": 1, "self": 0.05819149999999995 }, "TrainerController.start_learning": { "total": 26212.2943307, "count": 1, "self": 23.690154799714946, "children": { "TrainerController._reset_env": { "total": 3.7668695000000003, "count": 1, "self": 3.7668695000000003 }, "TrainerController.advance": { "total": 26184.666235600285, "count": 1004516, "self": 20.54277140076374, "children": { "env_step": { "total": 26164.12346419952, "count": 1004516, "self": 17152.511751000777, "children": { "SubprocessEnvManager._take_step": { "total": 8998.20145619884, "count": 1004516, "self": 43.404690699311686, "children": { "TorchPolicy.evaluate": { "total": 8954.796765499528, "count": 1000011, "self": 8954.796765499528 } } }, "workers": { "total": 13.410256999903122, "count": 1004516, "self": 0.0, "children": { "worker_root": { "total": 26186.88637710276, "count": 1004516, "is_parallel": true, "self": 9875.071289401678, "children": { "steps_from_proto": { "total": 0.00048389999999987054, "count": 1, "is_parallel": true, "self": 0.00012210000000045795, "children": { "_process_maybe_compressed_observation": { "total": 0.00025109999999983756, "count": 2, "is_parallel": true, "self": 3.3800000000194785e-05, "children": { "_observation_to_np_array": { "total": 0.00021729999999964278, "count": 3, "is_parallel": true, "self": 0.00021729999999964278 } } }, "_process_rank_one_or_two_observation": { "total": 0.00011069999999957503, "count": 2, "is_parallel": true, "self": 0.00011069999999957503 } } }, "UnityEnvironment.step": { "total": 16311.814603801084, "count": 1004516, "is_parallel": true, "self": 121.67509509960837, "children": { "UnityEnvironment._generate_step_input": { "total": 61.15591220182779, "count": 1004516, "is_parallel": true, "self": 61.15591220182779 }, "communicator.exchange": { "total": 15674.75046439934, "count": 1004516, "is_parallel": true, "self": 15674.75046439934 }, "steps_from_proto": { "total": 454.2331321003083, "count": 1004516, "is_parallel": true, "self": 106.32643739959605, "children": { "_process_maybe_compressed_observation": { "total": 287.21077120065667, "count": 2009032, "is_parallel": true, "self": 37.419722703589116, "children": { "_observation_to_np_array": { "total": 249.79104849706755, "count": 3016701, "is_parallel": true, "self": 249.79104849706755 } } }, "_process_rank_one_or_two_observation": { "total": 60.695923500055606, "count": 2009032, "is_parallel": true, "self": 60.695923500055606 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.369999831193127e-05, "count": 1, "self": 3.369999831193127e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 26187.903691299587, "count": 1386719, "is_parallel": true, "self": 56.37880670134837, "children": { "process_trajectory": { "total": 21975.25524539823, "count": 1386719, "is_parallel": true, "self": 21973.72103539823, "children": { "RLTrainer._checkpoint": { "total": 1.5342100000025312, "count": 6, "is_parallel": true, "self": 1.5342100000025312 } } }, "_update_policy": { "total": 4156.269639200007, "count": 277, "is_parallel": true, "self": 2784.3974990999604, "children": { "TorchPPOOptimizer.update": { "total": 1371.8721401000469, "count": 8490, "is_parallel": true, "self": 1371.8721401000469 } } } } } } } } }, "TrainerController._save_models": { "total": 0.17103710000083083, "count": 1, "self": 0.00504930000170134, "children": { "RLTrainer._checkpoint": { "total": 0.1659877999991295, "count": 1, "self": 0.1659877999991295 } } } } } } }