{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.5149146318435669, "min": 0.47257325053215027, "max": 2.855886459350586, "count": 200 }, "SnowballTarget.Policy.Entropy.sum": { "value": 5307.22509765625, "min": 4674.92919921875, "max": 29247.1328125, "count": 200 }, "SnowballTarget.Step.mean": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Step.sum": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.439998626708984, "min": 0.5547777414321899, "max": 14.509824752807617, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2960.19970703125, "min": 107.62687683105469, "max": 2969.9794921875, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0713995980847554, "min": 0.056072075512037925, "max": 0.07833578144188733, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.356997990423777, "min": 0.2242883020481517, "max": 0.38941264557754895, "count": 200 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.14004802061062233, "min": 0.12437470735269872, "max": 0.288974028738106, "count": 200 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7002401030531116, "min": 0.4974988294107949, "max": 1.3614779602663192, "count": 200 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.032997656000039e-07, "min": 7.032997656000039e-07, "max": 0.00029918820027059994, "count": 200 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.5164988280000196e-06, "min": 3.5164988280000196e-06, "max": 0.0014885160038279998, "count": 200 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10023440000000002, "min": 0.10023440000000002, "max": 0.1997294, "count": 200 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5011720000000001, "min": 0.4029176, "max": 0.996172, "count": 200 }, "SnowballTarget.Policy.Beta.mean": { "value": 2.1696560000000067e-05, "min": 2.1696560000000067e-05, "max": 0.004986497059999999, "count": 200 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00010848280000000034, "min": 0.00010848280000000034, "max": 0.024808982800000004, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 28.145454545454545, "min": 3.8636363636363638, "max": 28.69090909090909, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1548.0, "min": 170.0, "max": 1578.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 28.145454545454545, "min": 3.8636363636363638, "max": 28.69090909090909, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1548.0, "min": 170.0, "max": 1578.0, "count": 200 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1673440194", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.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": "1673444716" }, "total": 4521.2764975089995, "count": 1, "self": 0.43561067299924616, "children": { "run_training.setup": { "total": 0.11279566199999636, "count": 1, "self": 0.11279566199999636 }, "TrainerController.start_learning": { "total": 4520.728091174, "count": 1, "self": 6.14522325003054, "children": { "TrainerController._reset_env": { "total": 7.312251576999984, "count": 1, "self": 7.312251576999984 }, "TrainerController.advance": { "total": 4507.14964559397, "count": 181872, "self": 2.99756415482625, "children": { "env_step": { "total": 4504.152081439143, "count": 181872, "self": 2961.1008848273086, "children": { "SubprocessEnvManager._take_step": { "total": 1539.8872202998577, "count": 181872, "self": 15.248921755743822, "children": { "TorchPolicy.evaluate": { "total": 1524.638298544114, "count": 181872, "self": 347.8860426949343, "children": { "TorchPolicy.sample_actions": { "total": 1176.7522558491796, "count": 181872, "self": 1176.7522558491796 } } } } }, "workers": { "total": 3.1639763119770237, "count": 181872, "self": 0.0, "children": { "worker_root": { "total": 4507.101091094093, "count": 181872, "is_parallel": true, "self": 2134.72740012013, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007032643000002281, "count": 1, "is_parallel": true, "self": 0.004238931000031698, "children": { "_process_rank_one_or_two_observation": { "total": 0.002793711999970583, "count": 10, "is_parallel": true, "self": 0.002793711999970583 } } }, "UnityEnvironment.step": { "total": 0.04506874200001221, "count": 1, "is_parallel": true, "self": 0.0004459869999777766, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00032472000003735957, "count": 1, "is_parallel": true, "self": 0.00032472000003735957 }, "communicator.exchange": { "total": 0.042591763000018545, "count": 1, "is_parallel": true, "self": 0.042591763000018545 }, "steps_from_proto": { "total": 0.0017062719999785259, "count": 1, "is_parallel": true, "self": 0.0004770310000594691, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012292409999190568, "count": 10, "is_parallel": true, "self": 0.0012292409999190568 } } } } } } }, "UnityEnvironment.step": { "total": 2372.373690973963, "count": 181871, "is_parallel": true, "self": 89.00984772298034, "children": { "UnityEnvironment._generate_step_input": { "total": 53.160275872052864, "count": 181871, "is_parallel": true, "self": 53.160275872052864 }, "communicator.exchange": { "total": 1900.47967833504, "count": 181871, "is_parallel": true, "self": 1900.47967833504 }, "steps_from_proto": { "total": 329.7238890438902, "count": 181871, "is_parallel": true, "self": 72.65023522363532, "children": { "_process_rank_one_or_two_observation": { "total": 257.0736538202549, "count": 1818710, "is_parallel": true, "self": 257.0736538202549 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.8240000069199596e-05, "count": 1, "self": 4.8240000069199596e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 4476.866312538429, "count": 3592510, "is_parallel": true, "self": 95.54794549887356, "children": { "process_trajectory": { "total": 2540.1325051995514, "count": 3592510, "is_parallel": true, "self": 2531.2761401115517, "children": { "RLTrainer._checkpoint": { "total": 8.856365087999677, "count": 40, "is_parallel": true, "self": 8.856365087999677 } } }, "_update_policy": { "total": 1841.1858618400038, "count": 909, "is_parallel": true, "self": 482.45788304202483, "children": { "TorchPPOOptimizer.update": { "total": 1358.727978797979, "count": 46356, "is_parallel": true, "self": 1358.727978797979 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12092251299964119, "count": 1, "self": 0.0009361719994558371, "children": { "RLTrainer._checkpoint": { "total": 0.11998634100018535, "count": 1, "self": 0.11998634100018535 } } } } } } }