{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8240843415260315, "min": 0.8240843415260315, "max": 2.781203031539917, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 16316.8701171875, "min": 16316.8701171875, "max": 57025.7890625, "count": 10 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 19992.0, "max": 199984.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 19992.0, "max": 199984.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 4.4303412437438965, "min": 0.6376969814300537, "max": 4.430454730987549, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1767.7061767578125, "min": 254.44110107421875, "max": 1767.75146484375, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06543136699195426, "min": 0.06467241036740165, "max": 0.07208424894400915, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.5888823029275884, "min": 0.5820516933066149, "max": 0.6487582404960823, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1509266403343423, "min": 0.1286279910826378, "max": 0.2068020482598307, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.3583397630090808, "min": 1.1576519197437403, "max": 1.8612184343384763, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.1776094556000006e-05, "min": 2.1776094556000006e-05, "max": 0.00037817600545600005, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00019598485100400006, "min": 0.00019598485100400006, "max": 0.0034035840491040007, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10544400000000001, "min": 0.10544400000000001, "max": 0.19454400000000002, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.9489960000000001, "min": 0.9489960000000001, "max": 1.7508960000000002, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00028165560000000005, "min": 0.00028165560000000005, "max": 0.0047277456, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0025349004000000007, "min": 0.0025349004000000007, "max": 0.0425497104, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 19701.0, "min": 19701.0, "max": 19701.0, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.11111111111111, "min": 5.353535353535354, "max": 26.11111111111111, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 2585.0, "min": 530.0, "max": 2585.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.11111111111111, "min": 5.353535353535354, "max": 26.11111111111111, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 2585.0, "min": 530.0, "max": 2585.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1740277607", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740278037" }, "total": 429.8950610840001, "count": 1, "self": 0.8413907549999067, "children": { "run_training.setup": { "total": 0.02794771000003493, "count": 1, "self": 0.02794771000003493 }, "TrainerController.start_learning": { "total": 429.02572261900013, "count": 1, "self": 0.365293254993162, "children": { "TrainerController._reset_env": { "total": 2.8811776489999374, "count": 1, "self": 2.8811776489999374 }, "TrainerController.advance": { "total": 425.6487129480071, "count": 18192, "self": 0.3708912700226392, "children": { "env_step": { "total": 302.7683510909919, "count": 18192, "self": 230.66307755198, "children": { "SubprocessEnvManager._take_step": { "total": 71.88232142500863, "count": 18192, "self": 1.2864624970209206, "children": { "TorchPolicy.evaluate": { "total": 70.5958589279877, "count": 18192, "self": 70.5958589279877 } } }, "workers": { "total": 0.22295211400330572, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 427.2835901950008, "count": 18192, "is_parallel": true, "self": 225.29667332999986, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0053606809999564575, "count": 1, "is_parallel": true, "self": 0.0037981830001854178, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015624979997710398, "count": 10, "is_parallel": true, "self": 0.0015624979997710398 } } }, "UnityEnvironment.step": { "total": 0.035532583999952294, "count": 1, "is_parallel": true, "self": 0.0005835650000562964, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041134899993267027, "count": 1, "is_parallel": true, "self": 0.00041134899993267027 }, "communicator.exchange": { "total": 0.0327440309999929, "count": 1, "is_parallel": true, "self": 0.0327440309999929 }, "steps_from_proto": { "total": 0.001793638999970426, "count": 1, "is_parallel": true, "self": 0.00035460100002637773, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014390379999440484, "count": 10, "is_parallel": true, "self": 0.0014390379999440484 } } } } } } }, "UnityEnvironment.step": { "total": 201.98691686500092, "count": 18191, "is_parallel": true, "self": 9.708633568010441, "children": { "UnityEnvironment._generate_step_input": { "total": 5.464298686999314, "count": 18191, "is_parallel": true, "self": 5.464298686999314 }, "communicator.exchange": { "total": 155.21948031199508, "count": 18191, "is_parallel": true, "self": 155.21948031199508 }, "steps_from_proto": { "total": 31.59450429799608, "count": 18191, "is_parallel": true, "self": 5.7011395109879, "children": { "_process_rank_one_or_two_observation": { "total": 25.89336478700818, "count": 181910, "is_parallel": true, "self": 25.89336478700818 } } } } } } } } } } }, "trainer_advance": { "total": 122.5094705869925, "count": 18192, "self": 0.4303349359868207, "children": { "process_trajectory": { "total": 27.065201042006493, "count": 18192, "self": 26.473793939006327, "children": { "RLTrainer._checkpoint": { "total": 0.5914071030001651, "count": 4, "self": 0.5914071030001651 } } }, "_update_policy": { "total": 95.0139346089992, "count": 90, "self": 37.90074854899888, "children": { "TorchPPOOptimizer.update": { "total": 57.11318606000032, "count": 4587, "self": 57.11318606000032 } } } } } } }, "trainer_threads": { "total": 1.202000021294225e-06, "count": 1, "self": 1.202000021294225e-06 }, "TrainerController._save_models": { "total": 0.13053756499994051, "count": 1, "self": 0.0012505909999163123, "children": { "RLTrainer._checkpoint": { "total": 0.1292869740000242, "count": 1, "self": 0.1292869740000242 } } } } } } }