{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.3216782808303833, "min": 1.3216782808303833, "max": 2.8834047317504883, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 12619.3837890625, "min": 12619.3837890625, "max": 29592.3828125, "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": 11.707954406738281, "min": 0.226125106215477, "max": 11.707954406738281, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2283.051025390625, "min": 43.86827087402344, "max": 2347.169921875, "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.Losses.PolicyLoss.mean": { "value": 0.07054304578345824, "min": 0.06394238597056436, "max": 0.07360479509685212, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28217218313383297, "min": 0.25736847893676895, "max": 0.36190987325115953, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24640186766491215, "min": 0.0914473842481932, "max": 0.2683575829381452, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9856074706596486, "min": 0.3657895369927728, "max": 1.3312666701043354, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.694097306000002e-06, "min": 2.694097306000002e-06, "max": 9.7294002706e-05, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.0776389224000008e-05, "min": 1.0776389224000008e-05, "max": 0.0004617200382800001, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.197294, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 9.055060000000006e-05, "min": 9.055060000000006e-05, "max": 0.0029190906000000003, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00036220240000000024, "min": 0.00036220240000000024, "max": 0.013855428000000001, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 23.40909090909091, "min": 2.6136363636363638, "max": 23.40909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1030.0, "min": 115.0, "max": 1261.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.40909090909091, "min": 2.6136363636363638, "max": 23.40909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1030.0, "min": 115.0, "max": 1261.0, "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": "1682590480", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1682590982" }, "total": 501.68080369400013, "count": 1, "self": 0.42889803800017035, "children": { "run_training.setup": { "total": 0.11720615000012913, "count": 1, "self": 0.11720615000012913 }, "TrainerController.start_learning": { "total": 501.13469950599983, "count": 1, "self": 0.57686195696715, "children": { "TrainerController._reset_env": { "total": 3.863136655999824, "count": 1, "self": 3.863136655999824 }, "TrainerController.advance": { "total": 496.544205550033, "count": 18197, "self": 0.2849036070360853, "children": { "env_step": { "total": 496.2593019429969, "count": 18197, "self": 371.83671594501584, "children": { "SubprocessEnvManager._take_step": { "total": 124.14734737697518, "count": 18197, "self": 1.7621767459784223, "children": { "TorchPolicy.evaluate": { "total": 122.38517063099675, "count": 18197, "self": 122.38517063099675 } } }, "workers": { "total": 0.27523862100588303, "count": 18197, "self": 0.0, "children": { "worker_root": { "total": 499.53344662499694, "count": 18197, "is_parallel": true, "self": 247.61405376500716, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004670456999974704, "count": 1, "is_parallel": true, "self": 0.0033058900003197778, "children": { "_process_rank_one_or_two_observation": { "total": 0.001364566999654926, "count": 10, "is_parallel": true, "self": 0.001364566999654926 } } }, "UnityEnvironment.step": { "total": 0.037968624999848544, "count": 1, "is_parallel": true, "self": 0.000582373000042935, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036711199982164544, "count": 1, "is_parallel": true, "self": 0.00036711199982164544 }, "communicator.exchange": { "total": 0.034895277000032365, "count": 1, "is_parallel": true, "self": 0.034895277000032365 }, "steps_from_proto": { "total": 0.002123862999951598, "count": 1, "is_parallel": true, "self": 0.0004324699998505821, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016913930001010158, "count": 10, "is_parallel": true, "self": 0.0016913930001010158 } } } } } } }, "UnityEnvironment.step": { "total": 251.91939285998978, "count": 18196, "is_parallel": true, "self": 10.380015326972625, "children": { "UnityEnvironment._generate_step_input": { "total": 5.536308652009666, "count": 18196, "is_parallel": true, "self": 5.536308652009666 }, "communicator.exchange": { "total": 203.28506895500823, "count": 18196, "is_parallel": true, "self": 203.28506895500823 }, "steps_from_proto": { "total": 32.717999925999266, "count": 18196, "is_parallel": true, "self": 6.522596904067996, "children": { "_process_rank_one_or_two_observation": { "total": 26.19540302193127, "count": 181960, "is_parallel": true, "self": 26.19540302193127 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014398799999071343, "count": 1, "self": 0.00014398799999071343, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 492.94489132504737, "count": 424460, "is_parallel": true, "self": 10.66820210306264, "children": { "process_trajectory": { "total": 255.2104828349859, "count": 424460, "is_parallel": true, "self": 254.78312833098607, "children": { "RLTrainer._checkpoint": { "total": 0.42735450399982255, "count": 2, "is_parallel": true, "self": 0.42735450399982255 } } }, "_update_policy": { "total": 227.06620638699883, "count": 90, "is_parallel": true, "self": 88.15022115399688, "children": { "TorchPPOOptimizer.update": { "total": 138.91598523300195, "count": 6116, "is_parallel": true, "self": 138.91598523300195 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15035135499988428, "count": 1, "self": 0.0008800739999514917, "children": { "RLTrainer._checkpoint": { "total": 0.1494712809999328, "count": 1, "self": 0.1494712809999328 } } } } } } }