{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.7065010070800781, "min": 1.7065010070800781, "max": 2.888967752456665, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 16218.5859375, "min": 16218.5859375, "max": 29610.72265625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 7.674254417419434, "min": 0.03053261525928974, "max": 7.674254417419434, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1496.4796142578125, "min": 5.923327445983887, "max": 1499.783203125, "count": 20 }, "SnowballTarget.Policy.CuriosityValueEstimate.mean": { "value": 0.0971328467130661, "min": -0.02227313071489334, "max": 0.09728033095598221, "count": 20 }, "SnowballTarget.Policy.CuriosityValueEstimate.sum": { "value": 18.94090461730957, "min": -4.320987224578857, "max": 19.84518814086914, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 19.477272727272727, "min": 2.340909090909091, "max": 19.477272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 857.0, "min": 103.0, "max": 1065.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 19.477272727272727, "min": 2.340909090909091, "max": 19.477272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 857.0, "min": 103.0, "max": 1065.0, "count": 20 }, "SnowballTarget.Policy.CuriosityReward.mean": { "value": 0.19292364044072616, "min": 0.002482636821117591, "max": 0.29165254319933326, "count": 20 }, "SnowballTarget.Policy.CuriosityReward.sum": { "value": 8.48864017939195, "min": 0.109236020129174, "max": 16.04088987596333, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.035323625323180036, "min": 0.028463529926596617, "max": 0.04022655982978405, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.035323625323180036, "min": 0.028463529926596617, "max": 0.06431329781509132, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.15221274950925043, "min": 0.03654421540890254, "max": 0.16514313922208898, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.15221274950925043, "min": 0.03654421540890254, "max": 0.2702475930838024, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 9.732096756000008e-06, "min": 9.732096756000008e-06, "max": 0.00028693200435600004, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 9.732096756000008e-06, "min": 9.732096756000008e-06, "max": 0.000375864074712, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.103244, "min": 0.103244, "max": 0.19564399999999998, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.103244, "min": 0.103244, "max": 0.325288, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001718756000000001, "min": 0.0001718756000000001, "max": 0.0047826356000000006, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0001718756000000001, "min": 0.0001718756000000001, "max": 0.006271871200000001, "count": 20 }, "SnowballTarget.Losses.CuriosityForwardLoss.mean": { "value": 0.048212578921925785, "min": 0.046647274537998086, "max": 0.23560419240418604, "count": 20 }, "SnowballTarget.Losses.CuriosityForwardLoss.sum": { "value": 0.048212578921925785, "min": 0.046647274537998086, "max": 0.23560419240418604, "count": 20 }, "SnowballTarget.Losses.CuriosityInverseLoss.mean": { "value": 1.4837307976741416, "min": 1.4837307976741416, "max": 2.8772671877169143, "count": 20 }, "SnowballTarget.Losses.CuriosityInverseLoss.sum": { "value": 1.4837307976741416, "min": 1.4837307976741416, "max": 4.69676098169065, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1749399693", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1749400152" }, "total": 458.206854603, "count": 1, "self": 0.43880511700001534, "children": { "run_training.setup": { "total": 0.030700682999963647, "count": 1, "self": 0.030700682999963647 }, "TrainerController.start_learning": { "total": 457.73734880300003, "count": 1, "self": 0.4067580550084813, "children": { "TrainerController._reset_env": { "total": 3.601653650000003, "count": 1, "self": 3.601653650000003 }, "TrainerController.advance": { "total": 453.5602739069916, "count": 18192, "self": 0.42927635099442796, "children": { "env_step": { "total": 328.4490970089953, "count": 18192, "self": 248.02014741500318, "children": { "SubprocessEnvManager._take_step": { "total": 80.18965977799712, "count": 18192, "self": 1.3754845810066172, "children": { "TorchPolicy.evaluate": { "total": 78.8141751969905, "count": 18192, "self": 78.8141751969905 } } }, "workers": { "total": 0.23928981599499366, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 456.0009577290032, "count": 18192, "is_parallel": true, "self": 239.22472135201838, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005424476000030154, "count": 1, "is_parallel": true, "self": 0.003780675000029987, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016438010000001668, "count": 10, "is_parallel": true, "self": 0.0016438010000001668 } } }, "UnityEnvironment.step": { "total": 0.03824852800005374, "count": 1, "is_parallel": true, "self": 0.0005834369999320188, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047514600009890273, "count": 1, "is_parallel": true, "self": 0.00047514600009890273 }, "communicator.exchange": { "total": 0.03498555999999553, "count": 1, "is_parallel": true, "self": 0.03498555999999553 }, "steps_from_proto": { "total": 0.002204385000027287, "count": 1, "is_parallel": true, "self": 0.0004050629999028388, "children": { "_process_rank_one_or_two_observation": { "total": 0.001799322000124448, "count": 10, "is_parallel": true, "self": 0.001799322000124448 } } } } } } }, "UnityEnvironment.step": { "total": 216.7762363769848, "count": 18191, "is_parallel": true, "self": 10.13176079095706, "children": { "UnityEnvironment._generate_step_input": { "total": 5.904310303002148, "count": 18191, "is_parallel": true, "self": 5.904310303002148 }, "communicator.exchange": { "total": 166.5820600040056, "count": 18191, "is_parallel": true, "self": 166.5820600040056 }, "steps_from_proto": { "total": 34.15810527901999, "count": 18191, "is_parallel": true, "self": 6.311975488088365, "children": { "_process_rank_one_or_two_observation": { "total": 27.846129790931627, "count": 181910, "is_parallel": true, "self": 27.846129790931627 } } } } } } } } } } }, "trainer_advance": { "total": 124.68190054700187, "count": 18192, "self": 0.5112059669888822, "children": { "process_trajectory": { "total": 42.46871813801317, "count": 18192, "self": 41.67492808001316, "children": { "RLTrainer._checkpoint": { "total": 0.7937900580000132, "count": 4, "self": 0.7937900580000132 } } }, "_update_policy": { "total": 81.70197644199982, "count": 22, "self": 61.15012646799778, "children": { "TorchPPOOptimizer.update": { "total": 20.55184997400204, "count": 1122, "self": 20.55184997400204 } } } } } } }, "trainer_threads": { "total": 8.649999472254422e-07, "count": 1, "self": 8.649999472254422e-07 }, "TrainerController._save_models": { "total": 0.1686623260000033, "count": 1, "self": 0.00204728900007467, "children": { "RLTrainer._checkpoint": { "total": 0.16661503699992863, "count": 1, "self": 0.16661503699992863 } } } } } } }