{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.824944019317627, "min": 0.824944019317627, "max": 2.864058494567871, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7885.6396484375, "min": 7885.6396484375, "max": 29519.8515625, "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": 12.92063045501709, "min": 0.4513506591320038, "max": 12.92063045501709, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2519.52294921875, "min": 87.56202697753906, "max": 2617.27099609375, "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": 0.06825034915670461, "min": 0.06168837932089124, "max": 0.07328821549680131, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27300139662681844, "min": 0.2476472886542872, "max": 0.36326580912221984, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21978002530979177, "min": 0.11672845608372168, "max": 0.295886709847871, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8791201012391671, "min": 0.4669138243348867, "max": 1.4532033058942533, "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": 25.227272727272727, "min": 3.409090909090909, "max": 25.945454545454545, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1110.0, "min": 150.0, "max": 1427.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.227272727272727, "min": 3.409090909090909, "max": 25.945454545454545, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1110.0, "min": 150.0, "max": 1427.0, "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": "1682353719", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "1682354208" }, "total": 488.8262516279999, "count": 1, "self": 0.7377692300000263, "children": { "run_training.setup": { "total": 0.10972184199999901, "count": 1, "self": 0.10972184199999901 }, "TrainerController.start_learning": { "total": 487.9787605559999, "count": 1, "self": 0.5791288830151871, "children": { "TrainerController._reset_env": { "total": 3.7789744210000435, "count": 1, "self": 3.7789744210000435 }, "TrainerController.advance": { "total": 483.4022857179849, "count": 18220, "self": 0.32030631100167284, "children": { "env_step": { "total": 483.08197940698324, "count": 18220, "self": 351.37451275796843, "children": { "SubprocessEnvManager._take_step": { "total": 131.41694199301617, "count": 18220, "self": 1.787193425995497, "children": { "TorchPolicy.evaluate": { "total": 129.62974856702067, "count": 18220, "self": 129.62974856702067 } } }, "workers": { "total": 0.2905246559986381, "count": 18220, "self": 0.0, "children": { "worker_root": { "total": 486.3059530029866, "count": 18220, "is_parallel": true, "self": 227.09062992399458, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0052318739999464015, "count": 1, "is_parallel": true, "self": 0.003770359999862194, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014615140000842075, "count": 10, "is_parallel": true, "self": 0.0014615140000842075 } } }, "UnityEnvironment.step": { "total": 0.037446411000019, "count": 1, "is_parallel": true, "self": 0.0005797520001351586, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039290899997013184, "count": 1, "is_parallel": true, "self": 0.00039290899997013184 }, "communicator.exchange": { "total": 0.034433724999985316, "count": 1, "is_parallel": true, "self": 0.034433724999985316 }, "steps_from_proto": { "total": 0.0020400249999283915, "count": 1, "is_parallel": true, "self": 0.0004413990002376522, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015986259996907393, "count": 10, "is_parallel": true, "self": 0.0015986259996907393 } } } } } } }, "UnityEnvironment.step": { "total": 259.215323078992, "count": 18219, "is_parallel": true, "self": 10.610255451957187, "children": { "UnityEnvironment._generate_step_input": { "total": 5.90702276900015, "count": 18219, "is_parallel": true, "self": 5.90702276900015 }, "communicator.exchange": { "total": 207.64847594901835, "count": 18219, "is_parallel": true, "self": 207.64847594901835 }, "steps_from_proto": { "total": 35.04956890901633, "count": 18219, "is_parallel": true, "self": 7.0090129880368295, "children": { "_process_rank_one_or_two_observation": { "total": 28.0405559209795, "count": 182190, "is_parallel": true, "self": 28.0405559209795 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001338969998414541, "count": 1, "self": 0.0001338969998414541, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 479.38140093699315, "count": 442835, "is_parallel": true, "self": 11.428439956995248, "children": { "process_trajectory": { "total": 267.2913398519977, "count": 442835, "is_parallel": true, "self": 266.0547095009979, "children": { "RLTrainer._checkpoint": { "total": 1.2366303509998033, "count": 4, "is_parallel": true, "self": 1.2366303509998033 } } }, "_update_policy": { "total": 200.6616211280002, "count": 90, "is_parallel": true, "self": 72.5300479029944, "children": { "TorchPPOOptimizer.update": { "total": 128.1315732250058, "count": 4587, "is_parallel": true, "self": 128.1315732250058 } } } } } } } } }, "TrainerController._save_models": { "total": 0.21823763699990195, "count": 1, "self": 0.0011419800000567193, "children": { "RLTrainer._checkpoint": { "total": 0.21709565699984523, "count": 1, "self": 0.21709565699984523 } } } } } } }