{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9705596566200256, "min": 0.9396079182624817, "max": 2.8657326698303223, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9266.9033203125, "min": 9266.9033203125, "max": 29347.96875, "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": 12.767097473144531, "min": 0.2732199430465698, "max": 12.767097473144531, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2489.583984375, "min": 53.004669189453125, "max": 2591.41552734375, "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": 0.07208143992580053, "min": 0.06288313034272898, "max": 0.07566780452764885, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2883257597032021, "min": 0.2515325213709159, "max": 0.3724799186947719, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1921773000675089, "min": 0.10549601494544641, "max": 0.31751830488735555, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7687092002700356, "min": 0.42198405978178566, "max": 1.360899776804681, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.636363636363637, "min": 2.9318181818181817, "max": 25.563636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1084.0, "min": 129.0, "max": 1406.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.636363636363637, "min": 2.9318181818181817, "max": 25.563636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1084.0, "min": 129.0, "max": 1406.0, "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": "1675763138", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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=SnowballTarget2 --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1675763640" }, "total": 501.74091669200004, "count": 1, "self": 0.4238513210001429, "children": { "run_training.setup": { "total": 0.10433986700002151, "count": 1, "self": 0.10433986700002151 }, "TrainerController.start_learning": { "total": 501.2127255039999, "count": 1, "self": 0.6638759600011781, "children": { "TrainerController._reset_env": { "total": 9.300926713999957, "count": 1, "self": 9.300926713999957 }, "TrainerController.advance": { "total": 491.1174537729985, "count": 18201, "self": 0.3293899190140337, "children": { "env_step": { "total": 490.78806385398445, "count": 18201, "self": 340.39146412798334, "children": { "SubprocessEnvManager._take_step": { "total": 150.06358154799398, "count": 18201, "self": 1.6012495400020725, "children": { "TorchPolicy.evaluate": { "total": 148.4623320079919, "count": 18201, "self": 34.868927982985156, "children": { "TorchPolicy.sample_actions": { "total": 113.59340402500675, "count": 18201, "self": 113.59340402500675 } } } } }, "workers": { "total": 0.33301817800713707, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 499.43923154100025, "count": 18201, "is_parallel": true, "self": 235.70977812100034, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005292794999945727, "count": 1, "is_parallel": true, "self": 0.0032239170000138984, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020688779999318285, "count": 10, "is_parallel": true, "self": 0.0020688779999318285 } } }, "UnityEnvironment.step": { "total": 0.03643311200005428, "count": 1, "is_parallel": true, "self": 0.00039083299998310395, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00032212099995376775, "count": 1, "is_parallel": true, "self": 0.00032212099995376775 }, "communicator.exchange": { "total": 0.03381321700010176, "count": 1, "is_parallel": true, "self": 0.03381321700010176 }, "steps_from_proto": { "total": 0.0019069410000156495, "count": 1, "is_parallel": true, "self": 0.00043005400016227213, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014768869998533773, "count": 10, "is_parallel": true, "self": 0.0014768869998533773 } } } } } } }, "UnityEnvironment.step": { "total": 263.7294534199999, "count": 18200, "is_parallel": true, "self": 10.088950009011683, "children": { "UnityEnvironment._generate_step_input": { "total": 5.812290066994251, "count": 18200, "is_parallel": true, "self": 5.812290066994251 }, "communicator.exchange": { "total": 209.76217158296402, "count": 18200, "is_parallel": true, "self": 209.76217158296402 }, "steps_from_proto": { "total": 38.066041761029965, "count": 18200, "is_parallel": true, "self": 8.262915212027792, "children": { "_process_rank_one_or_two_observation": { "total": 29.803126549002172, "count": 182000, "is_parallel": true, "self": 29.803126549002172 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017959400020117755, "count": 1, "self": 0.00017959400020117755, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 487.4596505370654, "count": 448098, "is_parallel": true, "self": 11.215871075069572, "children": { "process_trajectory": { "total": 279.9540633229949, "count": 448098, "is_parallel": true, "self": 279.2322511289949, "children": { "RLTrainer._checkpoint": { "total": 0.7218121939999946, "count": 4, "is_parallel": true, "self": 0.7218121939999946 } } }, "_update_policy": { "total": 196.28971613900092, "count": 90, "is_parallel": true, "self": 68.03913676399225, "children": { "TorchPPOOptimizer.update": { "total": 128.25057937500867, "count": 4587, "is_parallel": true, "self": 128.25057937500867 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13028946300005373, "count": 1, "self": 0.000895096000022022, "children": { "RLTrainer._checkpoint": { "total": 0.1293943670000317, "count": 1, "self": 0.1293943670000317 } } } } } } }