{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1833347082138062, "min": 1.1833347082138062, "max": 2.8769798278808594, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11324.513671875, "min": 11324.513671875, "max": 29526.443359375, "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": 11.113080978393555, "min": 0.07073356211185455, "max": 11.113080978393555, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2167.05078125, "min": 13.722311019897461, "max": 2194.4580078125, "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.Environment.CumulativeReward.mean": { "value": 23.113636363636363, "min": 3.25, "max": 23.29090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1017.0, "min": 143.0, "max": 1281.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.113636363636363, "min": 3.25, "max": 23.29090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1017.0, "min": 143.0, "max": 1281.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07164471858271224, "min": 0.062384990135672294, "max": 0.07585342966984149, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.14328943716542447, "min": 0.12476998027134459, "max": 0.22756028900952446, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21838094893039442, "min": 0.11401407709937328, "max": 0.27878005671150546, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.43676189786078884, "min": 0.22802815419874656, "max": 0.8363401701345163, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 6.432097856000005e-06, "min": 6.432097856000005e-06, "max": 0.000290232003256, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.286419571200001e-05, "min": 1.286419571200001e-05, "max": 0.0007419960526679999, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10214399999999998, "min": 0.10214399999999998, "max": 0.19674400000000003, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.20428799999999997, "min": 0.20428799999999997, "max": 0.5473319999999999, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00011698560000000007, "min": 0.00011698560000000007, "max": 0.004837525599999998, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00023397120000000015, "min": 0.00023397120000000015, "max": 0.0123718668, "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": "1690819468", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690820144" }, "total": 676.065579782, "count": 1, "self": 0.5393505800000185, "children": { "run_training.setup": { "total": 0.05110353399999212, "count": 1, "self": 0.05110353399999212 }, "TrainerController.start_learning": { "total": 675.475125668, "count": 1, "self": 0.8121483389900277, "children": { "TrainerController._reset_env": { "total": 2.1541794759999675, "count": 1, "self": 2.1541794759999675 }, "TrainerController.advance": { "total": 672.29147469701, "count": 18205, "self": 0.3956082730072694, "children": { "env_step": { "total": 671.8958664240027, "count": 18205, "self": 562.3773612950133, "children": { "SubprocessEnvManager._take_step": { "total": 109.10618123799469, "count": 18205, "self": 2.844499962000839, "children": { "TorchPolicy.evaluate": { "total": 106.26168127599385, "count": 18205, "self": 106.26168127599385 } } }, "workers": { "total": 0.4123238909946849, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 673.1190867859951, "count": 18205, "is_parallel": true, "self": 344.1748832589853, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004471604000002571, "count": 1, "is_parallel": true, "self": 0.0026129749999199703, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018586290000826011, "count": 10, "is_parallel": true, "self": 0.0018586290000826011 } } }, "UnityEnvironment.step": { "total": 0.04600165899995545, "count": 1, "is_parallel": true, "self": 0.0008015829999976631, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004565360000015062, "count": 1, "is_parallel": true, "self": 0.0004565360000015062 }, "communicator.exchange": { "total": 0.04216569499999423, "count": 1, "is_parallel": true, "self": 0.04216569499999423 }, "steps_from_proto": { "total": 0.0025778449999620534, "count": 1, "is_parallel": true, "self": 0.0004778019998639138, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021000430000981396, "count": 10, "is_parallel": true, "self": 0.0021000430000981396 } } } } } } }, "UnityEnvironment.step": { "total": 328.94420352700985, "count": 18204, "is_parallel": true, "self": 14.68993989699942, "children": { "UnityEnvironment._generate_step_input": { "total": 7.887491835007097, "count": 18204, "is_parallel": true, "self": 7.887491835007097 }, "communicator.exchange": { "total": 258.98359614699643, "count": 18204, "is_parallel": true, "self": 258.98359614699643 }, "steps_from_proto": { "total": 47.3831756480069, "count": 18204, "is_parallel": true, "self": 9.443403564034838, "children": { "_process_rank_one_or_two_observation": { "total": 37.93977208397206, "count": 182040, "is_parallel": true, "self": 37.93977208397206 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00022650799996881688, "count": 1, "self": 0.00022650799996881688, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 665.5515257189005, "count": 728883, "is_parallel": true, "self": 17.463047892928103, "children": { "process_trajectory": { "total": 385.9351429879723, "count": 728883, "is_parallel": true, "self": 384.6503077559722, "children": { "RLTrainer._checkpoint": { "total": 1.2848352320000913, "count": 4, "is_parallel": true, "self": 1.2848352320000913 } } }, "_update_policy": { "total": 262.15333483800015, "count": 45, "is_parallel": true, "self": 84.49116405400014, "children": { "TorchPPOOptimizer.update": { "total": 177.662170784, "count": 4587, "is_parallel": true, "self": 177.662170784 } } } } } } } } }, "TrainerController._save_models": { "total": 0.21709664800005157, "count": 1, "self": 0.004119508000030692, "children": { "RLTrainer._checkpoint": { "total": 0.21297714000002088, "count": 1, "self": 0.21297714000002088 } } } } } } }