{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9811392426490784, "min": 0.9519923329353333, "max": 0.9945018291473389, "count": 3 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9411.087890625, "min": 700.1292724609375, "max": 9717.9375, "count": 3 }, "SnowballTarget.Step.mean": { "value": 499952.0, "min": 479960.0, "max": 499952.0, "count": 3 }, "SnowballTarget.Step.sum": { "value": 499952.0, "min": 479960.0, "max": 499952.0, "count": 3 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 118.75331115722656, "min": 117.22108459472656, "max": 118.75331115722656, "count": 3 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 24225.67578125, "min": 820.547607421875, "max": 24225.67578125, "count": 3 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07010364909062856, "min": 0.07010364909062856, "max": 0.0752406652269094, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3505182454531428, "min": 0.3009626609076376, "max": 0.3505182454531428, "count": 2 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 1.0401250626526628, "min": 1.0401250626526628, "max": 1.1791614168049658, "count": 2 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 5.200625313263314, "min": 4.716645667219863, "max": 5.200625313263314, "count": 2 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.0352989647999984e-06, "min": 1.0352989647999984e-06, "max": 3.0152969848000013e-06, "count": 2 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.176494823999992e-06, "min": 5.176494823999992e-06, "max": 1.2061187939200005e-05, "count": 2 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10103520000000002, "min": 0.10103520000000002, "max": 0.1030152, "count": 2 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5051760000000001, "min": 0.4120608, "max": 0.5051760000000001, "count": 2 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.165647999999992e-05, "min": 6.165647999999992e-05, "max": 0.00016045848000000008, "count": 2 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0003082823999999996, "min": 0.0003082823999999996, "max": 0.0006418339200000003, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.818181818181817, "min": 25.636363636363637, "max": 25.818181818181817, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1420.0, "min": 1128.0, "max": 1420.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.818181818181817, "min": 25.636363636363637, "max": 25.818181818181817, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1420.0, "min": 1128.0, "max": 1420.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1754451080", "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 --resume", "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": "1754451134" }, "total": 54.574341497000205, "count": 1, "self": 0.47651181600031123, "children": { "run_training.setup": { "total": 0.022783994999826973, "count": 1, "self": 0.022783994999826973 }, "TrainerController.start_learning": { "total": 54.07504568600007, "count": 1, "self": 0.04649125301011736, "children": { "TrainerController._reset_env": { "total": 2.255951511999683, "count": 1, "self": 2.255951511999683 }, "TrainerController.advance": { "total": 51.66140153299011, "count": 1864, "self": 0.04556924597454781, "children": { "env_step": { "total": 35.19539097300412, "count": 1864, "self": 26.57316563000677, "children": { "SubprocessEnvManager._take_step": { "total": 8.594578837008157, "count": 1864, "self": 0.14635792001445225, "children": { "TorchPolicy.evaluate": { "total": 8.448220916993705, "count": 1864, "self": 8.448220916993705 } } }, "workers": { "total": 0.027646505989196157, "count": 1864, "self": 0.0, "children": { "worker_root": { "total": 53.47082080098744, "count": 1864, "is_parallel": true, "self": 30.205245973983892, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002046512000106304, "count": 1, "is_parallel": true, "self": 0.000671051000153966, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013754609999523382, "count": 10, "is_parallel": true, "self": 0.0013754609999523382 } } }, "UnityEnvironment.step": { "total": 0.0355443829998876, "count": 1, "is_parallel": true, "self": 0.0005598339994321577, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003971500000261585, "count": 1, "is_parallel": true, "self": 0.0003971500000261585 }, "communicator.exchange": { "total": 0.03277499900013936, "count": 1, "is_parallel": true, "self": 0.03277499900013936 }, "steps_from_proto": { "total": 0.0018124000002899265, "count": 1, "is_parallel": true, "self": 0.00034252600016770884, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014698740001222177, "count": 10, "is_parallel": true, "self": 0.0014698740001222177 } } } } } } }, "UnityEnvironment.step": { "total": 23.265574827003547, "count": 1863, "is_parallel": true, "self": 1.086245167006382, "children": { "UnityEnvironment._generate_step_input": { "total": 0.5792968029982148, "count": 1863, "is_parallel": true, "self": 0.5792968029982148 }, "communicator.exchange": { "total": 18.181196178997652, "count": 1863, "is_parallel": true, "self": 18.181196178997652 }, "steps_from_proto": { "total": 3.4188366780012984, "count": 1863, "is_parallel": true, "self": 0.6422251270219022, "children": { "_process_rank_one_or_two_observation": { "total": 2.7766115509793963, "count": 18630, "is_parallel": true, "self": 2.7766115509793963 } } } } } } } } } } }, "trainer_advance": { "total": 16.42044131401144, "count": 1864, "self": 0.0626499330014667, "children": { "process_trajectory": { "total": 5.32722642500994, "count": 1864, "self": 5.188741588009634, "children": { "RLTrainer._checkpoint": { "total": 0.13848483700030556, "count": 1, "self": 0.13848483700030556 } } }, "_update_policy": { "total": 11.030564956000035, "count": 9, "self": 4.442429172993798, "children": { "TorchPPOOptimizer.update": { "total": 6.588135783006237, "count": 456, "self": 6.588135783006237 } } } } } } }, "trainer_threads": { "total": 1.0120002116309479e-06, "count": 1, "self": 1.0120002116309479e-06 }, "TrainerController._save_models": { "total": 0.11120037599994248, "count": 1, "self": 0.0010221789998468012, "children": { "RLTrainer._checkpoint": { "total": 0.11017819700009568, "count": 1, "self": 0.11017819700009568 } } } } } } }