{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.2989475727081299, "min": 1.2989475727081299, "max": 2.8550426959991455, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 12430.9287109375, "min": 12430.9287109375, "max": 29269.8984375, "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": 6.556441783905029, "min": 0.24515457451343536, "max": 6.556441783905029, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1278.506103515625, "min": 47.55998611450195, "max": 1318.5069580078125, "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": 0.0744377088457815, "min": 0.06297217409044285, "max": 0.0744377088457815, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.297750835383126, "min": 0.26214122091615166, "max": 0.3591708243697854, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1653894795488347, "min": 0.10575226593466462, "max": 0.211703825216083, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6615579181953388, "min": 0.4230090637386585, "max": 1.058519126080415, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082009730600007e-05, "min": 8.082009730600007e-05, "max": 0.0029188200027059994, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00032328038922400026, "min": 0.00032328038922400026, "max": 0.013851600038280001, "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": 0.00027913060000000025, "min": 0.00027913060000000025, "max": 0.0097296706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.001116522400000001, "min": 0.001116522400000001, "max": 0.046175827999999995, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.363636363636363, "min": 3.25, "max": 26.363636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1160.0, "min": 143.0, "max": 1384.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.363636363636363, "min": 3.25, "max": 26.363636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1160.0, "min": 143.0, "max": 1384.0, "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": "1692127728", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1692128294" }, "total": 566.0877201209998, "count": 1, "self": 0.4460372709997955, "children": { "run_training.setup": { "total": 0.04870341600002348, "count": 1, "self": 0.04870341600002348 }, "TrainerController.start_learning": { "total": 565.5929794340001, "count": 1, "self": 0.693533982992335, "children": { "TrainerController._reset_env": { "total": 4.101542884000025, "count": 1, "self": 4.101542884000025 }, "TrainerController.advance": { "total": 560.6383254530077, "count": 18203, "self": 0.32891178801605747, "children": { "env_step": { "total": 560.3094136649917, "count": 18203, "self": 418.23960517698595, "children": { "SubprocessEnvManager._take_step": { "total": 141.73969796400382, "count": 18203, "self": 2.0724833640016413, "children": { "TorchPolicy.evaluate": { "total": 139.66721460000218, "count": 18203, "self": 139.66721460000218 } } }, "workers": { "total": 0.33011052400189556, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 563.8085987549931, "count": 18203, "is_parallel": true, "self": 282.8449618249905, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005367127999988952, "count": 1, "is_parallel": true, "self": 0.0037127660000919604, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016543619998969916, "count": 10, "is_parallel": true, "self": 0.0016543619998969916 } } }, "UnityEnvironment.step": { "total": 0.036087665000025027, "count": 1, "is_parallel": true, "self": 0.0004655519999801072, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003551610000158689, "count": 1, "is_parallel": true, "self": 0.0003551610000158689 }, "communicator.exchange": { "total": 0.03298367000002145, "count": 1, "is_parallel": true, "self": 0.03298367000002145 }, "steps_from_proto": { "total": 0.0022832820000076026, "count": 1, "is_parallel": true, "self": 0.0006054600000879873, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016778219999196153, "count": 10, "is_parallel": true, "self": 0.0016778219999196153 } } } } } } }, "UnityEnvironment.step": { "total": 280.9636369300026, "count": 18202, "is_parallel": true, "self": 11.549474864004253, "children": { "UnityEnvironment._generate_step_input": { "total": 6.010329709990344, "count": 18202, "is_parallel": true, "self": 6.010329709990344 }, "communicator.exchange": { "total": 222.11056521799009, "count": 18202, "is_parallel": true, "self": 222.11056521799009 }, "steps_from_proto": { "total": 41.29326713801794, "count": 18202, "is_parallel": true, "self": 7.786154143028853, "children": { "_process_rank_one_or_two_observation": { "total": 33.507112994989086, "count": 182020, "is_parallel": true, "self": 33.507112994989086 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013296399993123487, "count": 1, "self": 0.00013296399993123487, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 556.3061459779769, "count": 494422, "is_parallel": true, "self": 12.060123563890784, "children": { "process_trajectory": { "total": 287.2826279630863, "count": 494422, "is_parallel": true, "self": 286.4477444230865, "children": { "RLTrainer._checkpoint": { "total": 0.8348835399998507, "count": 4, "is_parallel": true, "self": 0.8348835399998507 } } }, "_update_policy": { "total": 256.96339445099983, "count": 90, "is_parallel": true, "self": 108.86375061599313, "children": { "TorchPPOOptimizer.update": { "total": 148.0996438350067, "count": 6116, "is_parallel": true, "self": 148.0996438350067 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15944415000012668, "count": 1, "self": 0.0011983370000052673, "children": { "RLTrainer._checkpoint": { "total": 0.15824581300012142, "count": 1, "self": 0.15824581300012142 } } } } } } }