{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9609645009040833, "min": 0.9609645009040833, "max": 2.8558366298675537, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9175.2890625, "min": 9175.2890625, "max": 29246.623046875, "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": 12.784873008728027, "min": 0.4032527208328247, "max": 12.856180191040039, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2493.05029296875, "min": 78.23102569580078, "max": 2622.47705078125, "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": 0.06756487829960521, "min": 0.06273513498261524, "max": 0.07352856531084113, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27025951319842084, "min": 0.26304243126851007, "max": 0.36764282655420566, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21243829345878434, "min": 0.12582346639714626, "max": 0.30166247083860287, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8497531738351374, "min": 0.503293865588585, "max": 1.5083123541930143, "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": 25.0, "min": 3.522727272727273, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1100.0, "min": 155.0, "max": 1404.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.0, "min": 3.522727272727273, "max": 25.772727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1100.0, "min": 155.0, "max": 1404.0, "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": "1703310798", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/rlunit5_snowballtarget_config.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703311280" }, "total": 482.34055011299984, "count": 1, "self": 0.4883487120000609, "children": { "run_training.setup": { "total": 0.05262091899999177, "count": 1, "self": 0.05262091899999177 }, "TrainerController.start_learning": { "total": 481.7995804819998, "count": 1, "self": 0.618490681986259, "children": { "TrainerController._reset_env": { "total": 3.8921091040001556, "count": 1, "self": 3.8921091040001556 }, "TrainerController.advance": { "total": 477.1909499630133, "count": 18199, "self": 0.30492410501892664, "children": { "env_step": { "total": 476.88602585799435, "count": 18199, "self": 316.0489144680025, "children": { "SubprocessEnvManager._take_step": { "total": 160.53018003698753, "count": 18199, "self": 1.5809513899941976, "children": { "TorchPolicy.evaluate": { "total": 158.94922864699333, "count": 18199, "self": 158.94922864699333 } } }, "workers": { "total": 0.30693135300430185, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 480.1996489129965, "count": 18199, "is_parallel": true, "self": 237.20986877199994, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0060177789998761, "count": 1, "is_parallel": true, "self": 0.0039510349997726735, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020667440001034265, "count": 10, "is_parallel": true, "self": 0.0020667440001034265 } } }, "UnityEnvironment.step": { "total": 0.10739196800000173, "count": 1, "is_parallel": true, "self": 0.0006622420000894635, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004942959999425511, "count": 1, "is_parallel": true, "self": 0.0004942959999425511 }, "communicator.exchange": { "total": 0.10391914599995289, "count": 1, "is_parallel": true, "self": 0.10391914599995289 }, "steps_from_proto": { "total": 0.0023162840000168217, "count": 1, "is_parallel": true, "self": 0.0004295969999930094, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018866870000238123, "count": 10, "is_parallel": true, "self": 0.0018866870000238123 } } } } } } }, "UnityEnvironment.step": { "total": 242.98978014099657, "count": 18198, "is_parallel": true, "self": 11.358002597007271, "children": { "UnityEnvironment._generate_step_input": { "total": 5.889107147989762, "count": 18198, "is_parallel": true, "self": 5.889107147989762 }, "communicator.exchange": { "total": 188.86460700600423, "count": 18198, "is_parallel": true, "self": 188.86460700600423 }, "steps_from_proto": { "total": 36.878063389995305, "count": 18198, "is_parallel": true, "self": 6.904950019996477, "children": { "_process_rank_one_or_two_observation": { "total": 29.973113369998828, "count": 181980, "is_parallel": true, "self": 29.973113369998828 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014348600006997003, "count": 1, "self": 0.00014348600006997003, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 471.2783412450233, "count": 696532, "is_parallel": true, "self": 15.293727501918056, "children": { "process_trajectory": { "total": 260.9598128171051, "count": 696532, "is_parallel": true, "self": 260.32514924810516, "children": { "RLTrainer._checkpoint": { "total": 0.6346635689999403, "count": 4, "is_parallel": true, "self": 0.6346635689999403 } } }, "_update_policy": { "total": 195.02480092600013, "count": 90, "is_parallel": true, "self": 62.62581292899722, "children": { "TorchPPOOptimizer.update": { "total": 132.3989879970029, "count": 4587, "is_parallel": true, "self": 132.3989879970029 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09788724700001694, "count": 1, "self": 0.0010475290000613313, "children": { "RLTrainer._checkpoint": { "total": 0.09683971799995561, "count": 1, "self": 0.09683971799995561 } } } } } } }