{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.2727086544036865, "min": 1.2493765354156494, "max": 1.6013143062591553, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 12747.4501953125, "min": 11234.3935546875, "max": 17414.09765625, "count": 50 }, "Pyramids.Step.mean": { "value": 499968.0, "min": 9984.0, "max": 499968.0, "count": 50 }, "Pyramids.Step.sum": { "value": 499968.0, "min": 9984.0, "max": 499968.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.10029812902212143, "min": -0.10816387087106705, "max": 0.14089275896549225, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -16.2482967376709, "min": -17.08169174194336, "max": 21.979270935058594, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07181349275502383, "min": 0.06151249038197825, "max": 0.07925555710931703, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.2872539710200953, "min": 0.18919696086603732, "max": 0.3170222284372681, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 1.8274645853741735e-06, "min": 1.6312683027584915e-06, "max": 0.007418988164064483, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 7.309858341496694e-06, "min": 5.3569195657132695e-06, "max": 0.02225696449219345, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.3996988668000118e-06, "min": 3.3996988668000118e-06, "max": 0.0002967360010879999, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.3598795467200047e-05, "min": 1.3598795467200047e-05, "max": 0.0011407104197631998, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1011332, "min": 0.1011332, "max": 0.198912, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.4045328, "min": 0.308928, "max": 0.7802368000000001, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 6.654668000000019e-05, "min": 6.654668000000019e-05, "max": 0.0049457087999999995, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.00026618672000000077, "min": 0.00026618672000000077, "max": 0.01901381632, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 31 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 15984.0, "min": 15984.0, "max": 15984.0, "count": 31 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -1.0000000447034836, "min": -1.0000000447034836, "max": -1.0000000447034836, "count": 37 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -16.000000715255737, "min": -16.000000715255737, "max": -1.0000000447034836, "count": 37 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -1.0000000447034836, "min": -1.0000000447034836, "max": -1.0000000447034836, "count": 37 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -16.000000715255737, "min": -16.000000715255737, "max": -1.0000000447034836, "count": 37 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717145625", "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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717146438" }, "total": 813.324159061, "count": 1, "self": 0.547978472000068, "children": { "run_training.setup": { "total": 0.053944063000017195, "count": 1, "self": 0.053944063000017195 }, "TrainerController.start_learning": { "total": 812.722236526, "count": 1, "self": 0.9014221640391042, "children": { "TrainerController._reset_env": { "total": 2.425563771999805, "count": 1, "self": 2.425563771999805 }, "TrainerController.advance": { "total": 809.3082812739608, "count": 31287, "self": 0.4836925209333458, "children": { "env_step": { "total": 808.8245887530275, "count": 31287, "self": 606.9207013260138, "children": { "SubprocessEnvManager._take_step": { "total": 201.43797932301322, "count": 31287, "self": 3.4492631909924967, "children": { "TorchPolicy.evaluate": { "total": 197.98871613202073, "count": 31287, "self": 197.98871613202073 } } }, "workers": { "total": 0.4659081040003912, "count": 31287, "self": 0.0, "children": { "worker_root": { "total": 810.42135204699, "count": 31287, "is_parallel": true, "self": 330.64560168599064, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021282650000102876, "count": 1, "is_parallel": true, "self": 0.0006177669999942736, "children": { "_process_rank_one_or_two_observation": { "total": 0.001510498000016014, "count": 8, "is_parallel": true, "self": 0.001510498000016014 } } }, "UnityEnvironment.step": { "total": 0.05783864999989419, "count": 1, "is_parallel": true, "self": 0.0006515339998713898, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046502700001838093, "count": 1, "is_parallel": true, "self": 0.00046502700001838093 }, "communicator.exchange": { "total": 0.05486574399992605, "count": 1, "is_parallel": true, "self": 0.05486574399992605 }, "steps_from_proto": { "total": 0.0018563450000783632, "count": 1, "is_parallel": true, "self": 0.00036433199989005516, "children": { "_process_rank_one_or_two_observation": { "total": 0.001492013000188308, "count": 8, "is_parallel": true, "self": 0.001492013000188308 } } } } } } }, "UnityEnvironment.step": { "total": 479.7757503609994, "count": 31286, "is_parallel": true, "self": 16.622949227981508, "children": { "UnityEnvironment._generate_step_input": { "total": 10.859555129006367, "count": 31286, "is_parallel": true, "self": 10.859555129006367 }, "communicator.exchange": { "total": 403.1021480700126, "count": 31286, "is_parallel": true, "self": 403.1021480700126 }, "steps_from_proto": { "total": 49.19109793399889, "count": 31286, "is_parallel": true, "self": 10.100294532034468, "children": { "_process_rank_one_or_two_observation": { "total": 39.09080340196442, "count": 250288, "is_parallel": true, "self": 39.09080340196442 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001004570001441607, "count": 1, "self": 0.0001004570001441607, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 804.6010664660521, "count": 609568, "is_parallel": true, "self": 12.166614674982384, "children": { "process_trajectory": { "total": 314.1280561400695, "count": 609568, "is_parallel": true, "self": 312.87738200406943, "children": { "RLTrainer._checkpoint": { "total": 1.2506741360000433, "count": 10, "is_parallel": true, "self": 1.2506741360000433 } } }, "_update_policy": { "total": 478.30639565100023, "count": 180, "is_parallel": true, "self": 161.01593171797595, "children": { "TorchPPOOptimizer.update": { "total": 317.2904639330243, "count": 11586, "is_parallel": true, "self": 317.2904639330243 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08686885900010566, "count": 1, "self": 0.0013663210002050619, "children": { "RLTrainer._checkpoint": { "total": 0.0855025379999006, "count": 1, "self": 0.0855025379999006 } } } } } } }