{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8043879270553589, "min": 0.7842196226119995, "max": 2.8860089778900146, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7830.71630859375, "min": 7474.001953125, "max": 29682.603515625, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 6.1248393058776855, "min": 0.2707934081554413, "max": 6.174499034881592, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1255.592041015625, "min": 52.53392028808594, "max": 1265.7723388671875, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.060708725955905096, "min": 0.060708725955905096, "max": 0.07414255718079707, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3035436297795255, "min": 0.2504041273895578, "max": 0.3707127859039853, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17294281878892115, "min": 0.1161635343154308, "max": 0.26344290083529903, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8647140939446057, "min": 0.4646541372617232, "max": 1.2212318547216117, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.017698982400001e-06, "min": 1.017698982400001e-06, "max": 9.891760108239999e-05, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.088494912000005e-06, "min": 5.088494912000005e-06, "max": 0.0004846880153120001, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10101760000000001, "min": 0.10101760000000001, "max": 0.19891759999999997, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5050880000000001, "min": 0.41199040000000003, "max": 0.984688, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.0778240000000044e-05, "min": 6.0778240000000044e-05, "max": 0.00494598824, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0003038912000000002, "min": 0.0003038912000000002, "max": 0.0242359312, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 23.745454545454546, "min": 3.409090909090909, "max": 24.386363636363637, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1306.0, "min": 150.0, "max": 1320.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.745454545454546, "min": 3.409090909090909, "max": 24.386363636363637, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1306.0, "min": 150.0, "max": 1320.0, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688529378", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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 --force", "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": "1688530675" }, "total": 1296.3755296559998, "count": 1, "self": 0.7289389279999341, "children": { "run_training.setup": { "total": 0.07017150599995148, "count": 1, "self": 0.07017150599995148 }, "TrainerController.start_learning": { "total": 1295.576419222, "count": 1, "self": 1.7240856960406745, "children": { "TrainerController._reset_env": { "total": 4.705891947000055, "count": 1, "self": 4.705891947000055 }, "TrainerController.advance": { "total": 1288.910077131959, "count": 45496, "self": 0.8513227349444605, "children": { "env_step": { "total": 1288.0587543970146, "count": 45496, "self": 940.860480628, "children": { "SubprocessEnvManager._take_step": { "total": 346.40467174502965, "count": 45496, "self": 5.3291665920646665, "children": { "TorchPolicy.evaluate": { "total": 341.075505152965, "count": 45496, "self": 341.075505152965 } } }, "workers": { "total": 0.7936020239849313, "count": 45496, "self": 0.0, "children": { "worker_root": { "total": 1290.9500795880067, "count": 45496, "is_parallel": true, "self": 588.9418835629945, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029019309999966936, "count": 1, "is_parallel": true, "self": 0.0007515459992646356, "children": { "_process_rank_one_or_two_observation": { "total": 0.002150385000732058, "count": 10, "is_parallel": true, "self": 0.002150385000732058 } } }, "UnityEnvironment.step": { "total": 0.04356826299999739, "count": 1, "is_parallel": true, "self": 0.0006240079997041903, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003780090000873315, "count": 1, "is_parallel": true, "self": 0.0003780090000873315 }, "communicator.exchange": { "total": 0.04041348700002345, "count": 1, "is_parallel": true, "self": 0.04041348700002345 }, "steps_from_proto": { "total": 0.0021527590001824137, "count": 1, "is_parallel": true, "self": 0.00042292199987059576, "children": { "_process_rank_one_or_two_observation": { "total": 0.001729837000311818, "count": 10, "is_parallel": true, "self": 0.001729837000311818 } } } } } } }, "UnityEnvironment.step": { "total": 702.0081960250122, "count": 45495, "is_parallel": true, "self": 28.647195238912445, "children": { "UnityEnvironment._generate_step_input": { "total": 14.662951004022034, "count": 45495, "is_parallel": true, "self": 14.662951004022034 }, "communicator.exchange": { "total": 563.9191013540067, "count": 45495, "is_parallel": true, "self": 563.9191013540067 }, "steps_from_proto": { "total": 94.77894842807109, "count": 45495, "is_parallel": true, "self": 18.154684977043416, "children": { "_process_rank_one_or_two_observation": { "total": 76.62426345102767, "count": 454950, "is_parallel": true, "self": 76.62426345102767 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013876499997422798, "count": 1, "self": 0.00013876499997422798, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1278.830828025004, "count": 1262433, "is_parallel": true, "self": 28.386800095169292, "children": { "process_trajectory": { "total": 704.6856600878359, "count": 1262433, "is_parallel": true, "self": 701.2936676608365, "children": { "RLTrainer._checkpoint": { "total": 3.3919924269994226, "count": 10, "is_parallel": true, "self": 3.3919924269994226 } } }, "_update_policy": { "total": 545.7583678419987, "count": 227, "is_parallel": true, "self": 195.29288030098314, "children": { "TorchPPOOptimizer.update": { "total": 350.4654875410156, "count": 11574, "is_parallel": true, "self": 350.4654875410156 } } } } } } } } }, "TrainerController._save_models": { "total": 0.23622568200016758, "count": 1, "self": 0.002137240000138263, "children": { "RLTrainer._checkpoint": { "total": 0.23408844200002932, "count": 1, "self": 0.23408844200002932 } } } } } } }