{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9720919728279114, "min": 0.9720919728279114, "max": 2.848801851272583, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9313.61328125, "min": 9313.61328125, "max": 29331.263671875, "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": 12.819991111755371, "min": 0.4527420997619629, "max": 12.819991111755371, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2499.898193359375, "min": 87.83197021484375, "max": 2560.205810546875, "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": 0.07402360732535895, "min": 0.06200111851178328, "max": 0.07583482224745595, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2960944293014358, "min": 0.24800447404713313, "max": 0.3791741112372798, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20985081623874458, "min": 0.11845066004852746, "max": 0.30348939061457036, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8394032649549783, "min": 0.47380264019410984, "max": 1.4255962189579126, "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": 25.09090909090909, "min": 3.2045454545454546, "max": 25.618181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1104.0, "min": 141.0, "max": 1409.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.09090909090909, "min": 3.2045454545454546, "max": 25.618181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1104.0, "min": 141.0, "max": 1409.0, "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": "1692515534", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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 --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": "1692516005" }, "total": 471.238913528, "count": 1, "self": 0.8055263480000008, "children": { "run_training.setup": { "total": 0.04336223199999267, "count": 1, "self": 0.04336223199999267 }, "TrainerController.start_learning": { "total": 470.390024948, "count": 1, "self": 0.5726143689891501, "children": { "TrainerController._reset_env": { "total": 4.158820107000054, "count": 1, "self": 4.158820107000054 }, "TrainerController.advance": { "total": 465.42878176701095, "count": 18215, "self": 0.27785801100253593, "children": { "env_step": { "total": 465.1509237560084, "count": 18215, "self": 337.1667008849984, "children": { "SubprocessEnvManager._take_step": { "total": 127.70308724699817, "count": 18215, "self": 1.9737981489928984, "children": { "TorchPolicy.evaluate": { "total": 125.72928909800527, "count": 18215, "self": 125.72928909800527 } } }, "workers": { "total": 0.28113562401182435, "count": 18215, "self": 0.0, "children": { "worker_root": { "total": 468.7358840500026, "count": 18215, "is_parallel": true, "self": 220.13461079500638, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006646957000043585, "count": 1, "is_parallel": true, "self": 0.005119124000088959, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015278329999546258, "count": 10, "is_parallel": true, "self": 0.0015278329999546258 } } }, "UnityEnvironment.step": { "total": 0.04341631700003745, "count": 1, "is_parallel": true, "self": 0.000899776999972346, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003116269999736687, "count": 1, "is_parallel": true, "self": 0.0003116269999736687 }, "communicator.exchange": { "total": 0.03989954300004683, "count": 1, "is_parallel": true, "self": 0.03989954300004683 }, "steps_from_proto": { "total": 0.0023053700000446042, "count": 1, "is_parallel": true, "self": 0.00039997400006086536, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019053959999837389, "count": 10, "is_parallel": true, "self": 0.0019053959999837389 } } } } } } }, "UnityEnvironment.step": { "total": 248.60127325499622, "count": 18214, "is_parallel": true, "self": 10.586479647004637, "children": { "UnityEnvironment._generate_step_input": { "total": 5.23889736500638, "count": 18214, "is_parallel": true, "self": 5.23889736500638 }, "communicator.exchange": { "total": 197.0562031049925, "count": 18214, "is_parallel": true, "self": 197.0562031049925 }, "steps_from_proto": { "total": 35.71969313799269, "count": 18214, "is_parallel": true, "self": 6.447258966963375, "children": { "_process_rank_one_or_two_observation": { "total": 29.272434171029317, "count": 182140, "is_parallel": true, "self": 29.272434171029317 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016130299991345964, "count": 1, "self": 0.00016130299991345964, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 461.9059679430016, "count": 428903, "is_parallel": true, "self": 9.626449896000054, "children": { "process_trajectory": { "total": 253.74777452000183, "count": 428903, "is_parallel": true, "self": 252.26350831600166, "children": { "RLTrainer._checkpoint": { "total": 1.4842662040001642, "count": 4, "is_parallel": true, "self": 1.4842662040001642 } } }, "_update_policy": { "total": 198.53174352699972, "count": 90, "is_parallel": true, "self": 73.68473452899991, "children": { "TorchPPOOptimizer.update": { "total": 124.84700899799981, "count": 4584, "is_parallel": true, "self": 124.84700899799981 } } } } } } } } }, "TrainerController._save_models": { "total": 0.22964740199995504, "count": 1, "self": 0.0011745849999442726, "children": { "RLTrainer._checkpoint": { "total": 0.22847281700001076, "count": 1, "self": 0.22847281700001076 } } } } } } }