{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.7644643783569336, "min": 2.7644643783569336, "max": 2.8233444690704346, "count": 31 }, "SnowballTarget.Policy.Entropy.sum": { "value": 212.86375427246094, "min": 183.86073303222656, "max": 2463.22705078125, "count": 31 }, "SnowballTarget.Step.mean": { "value": 199960.0, "min": 184968.0, "max": 199960.0, "count": 31 }, "SnowballTarget.Step.sum": { "value": 199960.0, "min": 184968.0, "max": 199960.0, "count": 31 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 2.8804264068603516, "min": 2.6963953971862793, "max": 2.988704204559326, "count": 31 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 23.043411254882812, "min": 10.785581588745117, "max": 51.96919250488281, "count": 31 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 31 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 31 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 7 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 2189.0, "min": 2189.0, "max": 2189.0, "count": 7 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06333703348668766, "min": 0.058399054214104955, "max": 0.08776450733392838, "count": 6 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.06333703348668766, "min": 0.058399054214104955, "max": 0.08776450733392838, "count": 6 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.27091147765225054, "min": 0.20008490892017589, "max": 0.27091147765225054, "count": 6 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.27091147765225054, "min": 0.20008490892017589, "max": 0.27091147765225054, "count": 6 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.0889891200000003e-07, "min": 1.0889891200000003e-07, "max": 6.588934120000005e-07, "count": 6 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.0889891200000003e-07, "min": 1.0889891200000003e-07, "max": 6.588934120000005e-07, "count": 6 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.102176, "min": 0.102176, "max": 0.11317600000000001, "count": 6 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.102176, "min": 0.102176, "max": 0.11317600000000001, "count": 6 }, "SnowballTarget.Policy.Beta.mean": { "value": 1.0979200000000003e-05, "min": 1.0979200000000003e-05, "max": 1.5929200000000007e-05, "count": 6 }, "SnowballTarget.Policy.Beta.sum": { "value": 1.0979200000000003e-05, "min": 1.0979200000000003e-05, "max": 1.5929200000000007e-05, "count": 6 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 5.909090909090909, "min": 3.5, "max": 6.181818181818182, "count": 7 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 65.0, "min": 7.0, "max": 68.0, "count": 7 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 5.909090909090909, "min": 3.5, "max": 6.181818181818182, "count": 7 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 65.0, "min": 7.0, "max": 68.0, "count": 7 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701532572", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --resume --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701532646" }, "total": 73.80729216400005, "count": 1, "self": 1.0500653790004435, "children": { "run_training.setup": { "total": 0.20530081799961408, "count": 1, "self": 0.20530081799961408 }, "TrainerController.start_learning": { "total": 72.55192596699999, "count": 1, "self": 0.08717217499315666, "children": { "TrainerController._reset_env": { "total": 10.285466686999825, "count": 1, "self": 10.285466686999825 }, "TrainerController.advance": { "total": 61.920349600007285, "count": 1415, "self": 0.03446931900407435, "children": { "env_step": { "total": 61.88588028100321, "count": 1415, "self": 39.68546892700351, "children": { "SubprocessEnvManager._take_step": { "total": 22.17643904599845, "count": 1415, "self": 0.34156328198741903, "children": { "TorchPolicy.evaluate": { "total": 21.83487576401103, "count": 1415, "self": 21.83487576401103 } } }, "workers": { "total": 0.023972308001248166, "count": 1415, "self": 0.0, "children": { "worker_root": { "total": 72.35766457700265, "count": 1415, "is_parallel": true, "self": 52.11620357800848, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029400109997368418, "count": 1, "is_parallel": true, "self": 0.0008444869999948423, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020955239997419994, "count": 10, "is_parallel": true, "self": 0.0020955239997419994 } } }, "UnityEnvironment.step": { "total": 0.07016501599991898, "count": 1, "is_parallel": true, "self": 0.0006563909996657458, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003816600001300685, "count": 1, "is_parallel": true, "self": 0.0003816600001300685 }, "communicator.exchange": { "total": 0.06717049000008046, "count": 1, "is_parallel": true, "self": 0.06717049000008046 }, "steps_from_proto": { "total": 0.001956475000042701, "count": 1, "is_parallel": true, "self": 0.00036165600022286526, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015948189998198359, "count": 10, "is_parallel": true, "self": 0.0015948189998198359 } } } } } } }, "UnityEnvironment.step": { "total": 20.24146099899417, "count": 1414, "is_parallel": true, "self": 0.8418219600007433, "children": { "UnityEnvironment._generate_step_input": { "total": 0.40412465499412065, "count": 1414, "is_parallel": true, "self": 0.40412465499412065 }, "communicator.exchange": { "total": 16.377537276004205, "count": 1414, "is_parallel": true, "self": 16.377537276004205 }, "steps_from_proto": { "total": 2.6179771079951024, "count": 1414, "is_parallel": true, "self": 0.4715468080012215, "children": { "_process_rank_one_or_two_observation": { "total": 2.146430299993881, "count": 14140, "is_parallel": true, "self": 2.146430299993881 } } } } } } } } } } } } }, "trainer_threads": { "total": 9.725699965201784e-05, "count": 1, "self": 9.725699965201784e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 61.41551269196634, "count": 80656, "is_parallel": true, "self": 1.2501088620283554, "children": { "process_trajectory": { "total": 36.636185387938895, "count": 80656, "is_parallel": true, "self": 36.11438245993895, "children": { "RLTrainer._checkpoint": { "total": 0.5218029279999428, "count": 1, "is_parallel": true, "self": 0.5218029279999428 } } }, "_update_policy": { "total": 23.52921844199909, "count": 6, "is_parallel": true, "self": 14.409687215000304, "children": { "TorchPPOOptimizer.update": { "total": 9.119531226998788, "count": 303, "is_parallel": true, "self": 9.119531226998788 } } } } } } } } }, "TrainerController._save_models": { "total": 0.25884024800006955, "count": 1, "self": 0.002457770000091841, "children": { "RLTrainer._checkpoint": { "total": 0.2563824779999777, "count": 1, "self": 0.2563824779999777 } } } } } } }