{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0712509155273438, "min": 1.0712509155273438, "max": 2.8573763370513916, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10299.005859375, "min": 10299.005859375, "max": 29482.41015625, "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": 13.504627227783203, "min": 0.3727976679801941, "max": 13.546209335327148, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2633.40234375, "min": 72.32274627685547, "max": 2761.96435546875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.10244492174918457, "min": 0.09180860257243587, "max": 0.10516738792674218, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.4097796869967383, "min": 0.3789351996019832, "max": 0.5258369396337109, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16974813363733973, "min": 0.11526818767375913, "max": 0.2865908503970679, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6789925345493589, "min": 0.4610727506950365, "max": 1.4329542519853395, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.388097306000004e-06, "min": 5.388097306000004e-06, "max": 0.000194588002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.1552389224000015e-05, "min": 2.1552389224000015e-05, "max": 0.00092344003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.197294, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.9617200000000001, "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": 26.113636363636363, "min": 3.5681818181818183, "max": 26.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1149.0, "min": 157.0, "max": 1462.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.113636363636363, "min": 3.5681818181818183, "max": 26.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1149.0, "min": 157.0, "max": 1462.0, "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": "1682522398", "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": "1682522968" }, "total": 569.462394871, "count": 1, "self": 0.38286282100000335, "children": { "run_training.setup": { "total": 0.12662620399999014, "count": 1, "self": 0.12662620399999014 }, "TrainerController.start_learning": { "total": 568.952905846, "count": 1, "self": 0.5532228160057002, "children": { "TrainerController._reset_env": { "total": 4.878939495999987, "count": 1, "self": 4.878939495999987 }, "TrainerController.advance": { "total": 563.3269975349946, "count": 18206, "self": 0.2973197079846841, "children": { "env_step": { "total": 563.0296778270099, "count": 18206, "self": 435.56805113801784, "children": { "SubprocessEnvManager._take_step": { "total": 127.19088533699801, "count": 18206, "self": 1.712720168993087, "children": { "TorchPolicy.evaluate": { "total": 125.47816516800492, "count": 18206, "self": 125.47816516800492 } } }, "workers": { "total": 0.27074135199404736, "count": 18206, "self": 0.0, "children": { "worker_root": { "total": 567.3113274460138, "count": 18206, "is_parallel": true, "self": 330.63562882802347, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004773830000033286, "count": 1, "is_parallel": true, "self": 0.003281481000101394, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014923489999318917, "count": 10, "is_parallel": true, "self": 0.0014923489999318917 } } }, "UnityEnvironment.step": { "total": 0.08339220299995986, "count": 1, "is_parallel": true, "self": 0.0007312719999390538, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046834799996986476, "count": 1, "is_parallel": true, "self": 0.00046834799996986476 }, "communicator.exchange": { "total": 0.07890802500003247, "count": 1, "is_parallel": true, "self": 0.07890802500003247 }, "steps_from_proto": { "total": 0.003284558000018478, "count": 1, "is_parallel": true, "self": 0.0004911540000875902, "children": { "_process_rank_one_or_two_observation": { "total": 0.002793403999930888, "count": 10, "is_parallel": true, "self": 0.002793403999930888 } } } } } } }, "UnityEnvironment.step": { "total": 236.67569861799035, "count": 18205, "is_parallel": true, "self": 9.893020844986438, "children": { "UnityEnvironment._generate_step_input": { "total": 5.396190251010125, "count": 18205, "is_parallel": true, "self": 5.396190251010125 }, "communicator.exchange": { "total": 189.96181932899162, "count": 18205, "is_parallel": true, "self": 189.96181932899162 }, "steps_from_proto": { "total": 31.424668193002162, "count": 18205, "is_parallel": true, "self": 6.247801284025741, "children": { "_process_rank_one_or_two_observation": { "total": 25.17686690897642, "count": 182050, "is_parallel": true, "self": 25.17686690897642 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017865999984678638, "count": 1, "self": 0.00017865999984678638, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 560.2188053240034, "count": 375435, "is_parallel": true, "self": 9.302462896004954, "children": { "process_trajectory": { "total": 265.6920619909984, "count": 375435, "is_parallel": true, "self": 264.0345686429984, "children": { "RLTrainer._checkpoint": { "total": 1.6574933480000027, "count": 4, "is_parallel": true, "self": 1.6574933480000027 } } }, "_update_policy": { "total": 285.22428043699995, "count": 90, "is_parallel": true, "self": 80.46977651000145, "children": { "TorchPPOOptimizer.update": { "total": 204.7545039269985, "count": 12236, "is_parallel": true, "self": 204.7545039269985 } } } } } } } } }, "TrainerController._save_models": { "total": 0.19356733899985556, "count": 1, "self": 0.0010683589998734533, "children": { "RLTrainer._checkpoint": { "total": 0.1924989799999821, "count": 1, "self": 0.1924989799999821 } } } } } } }