{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.897666335105896, "min": 0.897666335105896, "max": 2.8646047115325928, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8570.91796875, "min": 8570.91796875, "max": 29336.416015625, "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": 12.505200386047363, "min": 0.26092207431793213, "max": 12.505200386047363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2438.51416015625, "min": 50.6188850402832, "max": 2507.44970703125, "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": 0.07361195802770774, "min": 0.06342428667424017, "max": 0.07415563978857416, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.294447832110831, "min": 0.2536971466969607, "max": 0.3707781989428708, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1967912930995226, "min": 0.10561362731210001, "max": 0.2979418669845544, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7871651723980904, "min": 0.42245450924840006, "max": 1.489709334922772, "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": 25.386363636363637, "min": 3.159090909090909, "max": 25.386363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1117.0, "min": 139.0, "max": 1356.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.386363636363637, "min": 3.159090909090909, "max": 25.386363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1117.0, "min": 139.0, "max": 1356.0, "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": "1673862424", "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": "1673862869" }, "total": 445.10495671500007, "count": 1, "self": 0.3838378289999582, "children": { "run_training.setup": { "total": 0.10728999200000544, "count": 1, "self": 0.10728999200000544 }, "TrainerController.start_learning": { "total": 444.6138288940001, "count": 1, "self": 0.5983858240012978, "children": { "TrainerController._reset_env": { "total": 9.661477733999845, "count": 1, "self": 9.661477733999845 }, "TrainerController.advance": { "total": 434.23373718799894, "count": 18204, "self": 0.32447260402068423, "children": { "env_step": { "total": 433.90926458397826, "count": 18204, "self": 284.89696245493246, "children": { "SubprocessEnvManager._take_step": { "total": 148.71244434101618, "count": 18204, "self": 1.395030058025668, "children": { "TorchPolicy.evaluate": { "total": 147.3174142829905, "count": 18204, "self": 32.80437121898967, "children": { "TorchPolicy.sample_actions": { "total": 114.51304306400084, "count": 18204, "self": 114.51304306400084 } } } } }, "workers": { "total": 0.2998577880296125, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 443.2738859250003, "count": 18204, "is_parallel": true, "self": 212.53509527600727, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006387079999967682, "count": 1, "is_parallel": true, "self": 0.0042088450002211175, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021782349997465644, "count": 10, "is_parallel": true, "self": 0.0021782349997465644 } } }, "UnityEnvironment.step": { "total": 0.04274029800012613, "count": 1, "is_parallel": true, "self": 0.0005158310000297206, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030396300007851096, "count": 1, "is_parallel": true, "self": 0.00030396300007851096 }, "communicator.exchange": { "total": 0.04005158999984815, "count": 1, "is_parallel": true, "self": 0.04005158999984815 }, "steps_from_proto": { "total": 0.0018689140001697524, "count": 1, "is_parallel": true, "self": 0.00042047600027217413, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014484379998975783, "count": 10, "is_parallel": true, "self": 0.0014484379998975783 } } } } } } }, "UnityEnvironment.step": { "total": 230.73879064899302, "count": 18203, "is_parallel": true, "self": 8.917231241994841, "children": { "UnityEnvironment._generate_step_input": { "total": 5.000767162001239, "count": 18203, "is_parallel": true, "self": 5.000767162001239 }, "communicator.exchange": { "total": 182.91048395300186, "count": 18203, "is_parallel": true, "self": 182.91048395300186 }, "steps_from_proto": { "total": 33.91030829199508, "count": 18203, "is_parallel": true, "self": 6.9974667130195485, "children": { "_process_rank_one_or_two_observation": { "total": 26.91284157897553, "count": 182030, "is_parallel": true, "self": 26.91284157897553 } } } } } } } } } } } } }, "trainer_threads": { "total": 5.979900015518069e-05, "count": 1, "self": 5.979900015518069e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 431.33404714090284, "count": 358462, "is_parallel": true, "self": 9.607829572790934, "children": { "process_trajectory": { "total": 246.81866949911182, "count": 358462, "is_parallel": true, "self": 245.97134915111155, "children": { "RLTrainer._checkpoint": { "total": 0.8473203480002667, "count": 4, "is_parallel": true, "self": 0.8473203480002667 } } }, "_update_policy": { "total": 174.9075480690001, "count": 90, "is_parallel": true, "self": 43.27433311200434, "children": { "TorchPPOOptimizer.update": { "total": 131.63321495699574, "count": 4584, "is_parallel": true, "self": 131.63321495699574 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12016834899986861, "count": 1, "self": 0.0008789099997557059, "children": { "RLTrainer._checkpoint": { "total": 0.1192894390001129, "count": 1, "self": 0.1192894390001129 } } } } } } }