{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8508138656616211, "min": 0.8508138656616211, "max": 2.8748536109924316, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8142.28857421875, "min": 8142.28857421875, "max": 29472.998046875, "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": 12.938088417053223, "min": 0.3372732698917389, "max": 12.938088417053223, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2522.92724609375, "min": 65.43101501464844, "max": 2615.3017578125, "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": 0.06748798384054966, "min": 0.06327158858378727, "max": 0.07311450559659444, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26995193536219864, "min": 0.26279000006901443, "max": 0.35340288747330284, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22136960952889684, "min": 0.10948635912135096, "max": 0.28567397255523536, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8854784381155874, "min": 0.43794543648540385, "max": 1.4283698627761767, "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": 25.363636363636363, "min": 3.2954545454545454, "max": 25.618181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1116.0, "min": 145.0, "max": 1409.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.363636363636363, "min": 3.2954545454545454, "max": 25.618181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1116.0, "min": 145.0, "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": "1736262046", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736262735" }, "total": 689.2594084500001, "count": 1, "self": 0.580462672000067, "children": { "run_training.setup": { "total": 0.07864409100000103, "count": 1, "self": 0.07864409100000103 }, "TrainerController.start_learning": { "total": 688.6003016870001, "count": 1, "self": 1.1087022589850903, "children": { "TrainerController._reset_env": { "total": 8.094078056, "count": 1, "self": 8.094078056 }, "TrainerController.advance": { "total": 679.3022128660149, "count": 18203, "self": 0.5056011470146586, "children": { "env_step": { "total": 678.7966117190002, "count": 18203, "self": 517.9907022599835, "children": { "SubprocessEnvManager._take_step": { "total": 160.31878295500712, "count": 18203, "self": 2.9596565810173843, "children": { "TorchPolicy.evaluate": { "total": 157.35912637398974, "count": 18203, "self": 157.35912637398974 } } }, "workers": { "total": 0.48712650400955226, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 686.1970164429974, "count": 18203, "is_parallel": true, "self": 320.4376626789939, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00286728999992647, "count": 1, "is_parallel": true, "self": 0.0008757809998769517, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019915090000495184, "count": 10, "is_parallel": true, "self": 0.0019915090000495184 } } }, "UnityEnvironment.step": { "total": 0.047072768000020915, "count": 1, "is_parallel": true, "self": 0.0009865180001042972, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005405469999004708, "count": 1, "is_parallel": true, "self": 0.0005405469999004708 }, "communicator.exchange": { "total": 0.04293568499997491, "count": 1, "is_parallel": true, "self": 0.04293568499997491 }, "steps_from_proto": { "total": 0.0026100180000412365, "count": 1, "is_parallel": true, "self": 0.0005323800000951451, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020776379999460914, "count": 10, "is_parallel": true, "self": 0.0020776379999460914 } } } } } } }, "UnityEnvironment.step": { "total": 365.75935376400355, "count": 18202, "is_parallel": true, "self": 17.355945103014278, "children": { "UnityEnvironment._generate_step_input": { "total": 8.639288336993104, "count": 18202, "is_parallel": true, "self": 8.639288336993104 }, "communicator.exchange": { "total": 290.2291254969873, "count": 18202, "is_parallel": true, "self": 290.2291254969873 }, "steps_from_proto": { "total": 49.53499482700886, "count": 18202, "is_parallel": true, "self": 10.185416855987341, "children": { "_process_rank_one_or_two_observation": { "total": 39.34957797102152, "count": 182020, "is_parallel": true, "self": 39.34957797102152 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0004112569999961124, "count": 1, "self": 0.0004112569999961124, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 671.6883091399385, "count": 912538, "is_parallel": true, "self": 20.06140061992653, "children": { "process_trajectory": { "total": 373.3787353360116, "count": 912538, "is_parallel": true, "self": 371.88843277601154, "children": { "RLTrainer._checkpoint": { "total": 1.490302560000032, "count": 4, "is_parallel": true, "self": 1.490302560000032 } } }, "_update_policy": { "total": 278.2481731840004, "count": 90, "is_parallel": true, "self": 67.71833141100001, "children": { "TorchPPOOptimizer.update": { "total": 210.52984177300038, "count": 4587, "is_parallel": true, "self": 210.52984177300038 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09489724900004148, "count": 1, "self": 0.0014806230001340737, "children": { "RLTrainer._checkpoint": { "total": 0.09341662599990741, "count": 1, "self": 0.09341662599990741 } } } } } } }