{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4732387363910675, "min": 0.46456775069236755, "max": 1.5208418369293213, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14454.603515625, "min": 13899.8671875, "max": 46136.2578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989973.0, "min": 29934.0, "max": 989973.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989973.0, "min": 29934.0, "max": 989973.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5489568710327148, "min": -0.18212325870990753, "max": 0.5831024050712585, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 152.61001586914062, "min": -43.163211822509766, "max": 162.68557739257812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -1.2688008546829224, "min": -1.2688008546829224, "max": 0.4554428458213806, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -352.7266540527344, "min": -352.7266540527344, "max": 107.93995666503906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07093064914818974, "min": 0.06423239169784614, "max": 0.07235053450137205, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9930290880746564, "min": 0.5011395681140965, "max": 1.0711536195691829, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.1653442146810599, "min": 0.00010283258653561238, "max": 0.1653442146810599, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 2.3148190055348383, "min": 0.001336823624962961, "max": 2.3148190055348383, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.259133294607143e-06, "min": 7.259133294607143e-06, "max": 0.00029523368730305713, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001016278661245, "min": 0.0001016278661245, "max": 0.0035093099302300995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024196785714286, "min": 0.1024196785714286, "max": 0.19841122857142857, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338755000000003, "min": 1.3888786, "max": 2.5697699, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002517258892857143, "min": 0.0002517258892857143, "max": 0.009841281734285712, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00352416245, "min": 0.00352416245, "max": 0.11700001301, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011892594397068024, "min": 0.011687462218105793, "max": 0.3864750266075134, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16649632155895233, "min": 0.16362446546554565, "max": 2.705325126647949, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 370.8641975308642, "min": 333.7816091954023, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30040.0, "min": 16733.0, "max": 32396.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5807012096967226, "min": -0.9999548908202879, "max": 1.6432183772839348, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 128.03679798543453, "min": -31.99360166490078, "max": 142.95999882370234, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5807012096967226, "min": -0.9999548908202879, "max": 1.6432183772839348, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 128.03679798543453, "min": -31.99360166490078, "max": 142.95999882370234, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.045621416668758304, "min": 0.041157531930701055, "max": 7.6459359693176605, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6953347501694225, "min": 3.580705277970992, "max": 129.98091147840023, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1707038004", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707040212" }, "total": 2207.848844487, "count": 1, "self": 0.5310461310000392, "children": { "run_training.setup": { "total": 0.08685310600003504, "count": 1, "self": 0.08685310600003504 }, "TrainerController.start_learning": { "total": 2207.23094525, "count": 1, "self": 1.3491721259533733, "children": { "TrainerController._reset_env": { "total": 2.953743874999873, "count": 1, "self": 2.953743874999873 }, "TrainerController.advance": { "total": 2202.838695998046, "count": 63655, "self": 1.4529343749818509, "children": { "env_step": { "total": 1555.2516809680665, "count": 63655, "self": 1422.2122332520785, "children": { "SubprocessEnvManager._take_step": { "total": 132.1737683370361, "count": 63655, "self": 4.774521102196104, "children": { "TorchPolicy.evaluate": { "total": 127.39924723484, "count": 62552, "self": 127.39924723484 } } }, "workers": { "total": 0.8656793789518815, "count": 63655, "self": 0.0, "children": { "worker_root": { "total": 2202.1310441380656, "count": 63655, "is_parallel": true, "self": 897.8805398911154, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029949600002510124, "count": 1, "is_parallel": true, "self": 0.0009159220007859403, "children": { "_process_rank_one_or_two_observation": { "total": 0.002079037999465072, "count": 8, "is_parallel": true, "self": 0.002079037999465072 } } }, "UnityEnvironment.step": { "total": 0.049345730999903026, "count": 1, "is_parallel": true, "self": 0.0005944359995737614, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005383470002016111, "count": 1, "is_parallel": true, "self": 0.0005383470002016111 }, "communicator.exchange": { "total": 0.04651662400010537, "count": 1, "is_parallel": true, "self": 0.04651662400010537 }, "steps_from_proto": { "total": 0.0016963240000222868, "count": 1, "is_parallel": true, "self": 0.00035250299970357446, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013438210003187123, "count": 8, "is_parallel": true, "self": 0.0013438210003187123 } } } } } } }, "UnityEnvironment.step": { "total": 1304.2505042469502, "count": 63654, "is_parallel": true, "self": 36.007895732122506, "children": { "UnityEnvironment._generate_step_input": { "total": 24.981384878814424, "count": 63654, "is_parallel": true, "self": 24.981384878814424 }, "communicator.exchange": { "total": 1141.5022200689905, "count": 63654, "is_parallel": true, "self": 1141.5022200689905 }, "steps_from_proto": { "total": 101.75900356702277, "count": 63654, "is_parallel": true, "self": 20.32271977162918, "children": { "_process_rank_one_or_two_observation": { "total": 81.43628379539359, "count": 509232, "is_parallel": true, "self": 81.43628379539359 } } } } } } } } } } }, "trainer_advance": { "total": 646.1340806549979, "count": 63655, "self": 2.699905676285198, "children": { "process_trajectory": { "total": 127.89687590672429, "count": 63655, "self": 127.68962765272454, "children": { "RLTrainer._checkpoint": { "total": 0.2072482539997509, "count": 2, "self": 0.2072482539997509 } } }, "_update_policy": { "total": 515.5372990719884, "count": 451, "self": 303.3176037730791, "children": { "TorchPPOOptimizer.update": { "total": 212.2196952989093, "count": 22812, "self": 212.2196952989093 } } } } } } }, "trainer_threads": { "total": 8.600000001024455e-07, "count": 1, "self": 8.600000001024455e-07 }, "TrainerController._save_models": { "total": 0.08933239100042556, "count": 1, "self": 0.001975512000171875, "children": { "RLTrainer._checkpoint": { "total": 0.08735687900025368, "count": 1, "self": 0.08735687900025368 } } } } } } }