{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.19460135698318481, "min": 0.18636582791805267, "max": 1.5099765062332153, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5859.8359375, "min": 5568.44189453125, "max": 45806.6484375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999971.0, "min": 29952.0, "max": 2999971.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999971.0, "min": 29952.0, "max": 2999971.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7857797145843506, "min": -0.15784014761447906, "max": 0.8184680938720703, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 231.8050079345703, "min": -37.40811538696289, "max": 246.35890197753906, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.005195184610784054, "min": -0.014911673963069916, "max": 0.23277071118354797, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.5325794219970703, "min": -4.458590507507324, "max": 56.097740173339844, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0667547960332771, "min": 0.064240590214557, "max": 0.07304095351303529, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9345671444658793, "min": 0.4952545778845282, "max": 1.0780114512890575, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013523975852632332, "min": 0.0014478023067269483, "max": 0.015534952509915458, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18933566193685264, "min": 0.018821429987450327, "max": 0.23302428764873187, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5332852032238124e-06, "min": 1.5332852032238124e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1465992845133373e-05, "min": 2.1465992845133373e-05, "max": 0.004011277062907667, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10051106190476193, "min": 0.10051106190476193, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4071548666666671, "min": 1.3962282666666668, "max": 2.8124971333333337, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.10550842857144e-05, "min": 6.10550842857144e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008547711800000016, "min": 0.0008547711800000016, "max": 0.1337155241, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0034966375678777695, "min": 0.003315959358587861, "max": 0.3480061888694763, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.04895292595028877, "min": 0.04642343148589134, "max": 2.4360432624816895, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 238.45, "min": 227.6766917293233, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28614.0, "min": 15984.0, "max": 32615.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.76688332259655, "min": -1.0000000521540642, "max": 1.76688332259655, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 212.025998711586, "min": -30.647001668810844, "max": 235.59999800473452, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.76688332259655, "min": -1.0000000521540642, "max": 1.76688332259655, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 212.025998711586, "min": -30.647001668810844, "max": 235.59999800473452, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.008593980252589973, "min": 0.008164096724300832, "max": 7.117798731662333, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.0312776303107967, "min": 0.9490190982978675, "max": 113.88477970659733, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1657380886", "python_version": "3.8.13 (default, Mar 28 2022, 11:38:47) \n[GCC 7.5.0]", "command_line_arguments": "/home/nm/anaconda3/envs/ml-agents/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.23.1", "end_time_seconds": "1657384806" }, "total": 3920.108843479, "count": 1, "self": 0.26874179399965215, "children": { "run_training.setup": { "total": 0.01050612499966519, "count": 1, "self": 0.01050612499966519 }, "TrainerController.start_learning": { "total": 3919.8295955600006, "count": 1, "self": 1.955553564357615, "children": { "TrainerController._reset_env": { "total": 2.3968844060000265, "count": 1, "self": 2.3968844060000265 }, "TrainerController.advance": { "total": 3915.419407417643, "count": 194844, "self": 1.9186068810231518, "children": { "env_step": { "total": 2551.216263735834, "count": 194844, "self": 2384.312934711892, "children": { "SubprocessEnvManager._take_step": { "total": 165.71205485480914, "count": 194844, "self": 6.306949509955302, "children": { "TorchPolicy.evaluate": { "total": 159.40510534485384, "count": 187556, "self": 52.33150703052161, "children": { "TorchPolicy.sample_actions": { "total": 107.07359831433223, "count": 187556, "self": 107.07359831433223 } } } } }, "workers": { "total": 1.1912741691330666, "count": 194844, "self": 0.0, "children": { "worker_root": { "total": 3915.4867073874548, "count": 194844, "is_parallel": true, "self": 1708.8440050286463, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016829500000312692, "count": 1, "is_parallel": true, "self": 0.0004736800001410302, "children": { "_process_rank_one_or_two_observation": { "total": 0.001209269999890239, "count": 8, "is_parallel": true, "self": 0.001209269999890239 } } }, "UnityEnvironment.step": { "total": 0.02834247700047854, "count": 1, "is_parallel": true, "self": 0.00046319000102812424, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037626899938913994, "count": 1, "is_parallel": true, "self": 0.00037626899938913994 }, "communicator.exchange": { "total": 0.026247959000102128, "count": 1, "is_parallel": true, "self": 0.026247959000102128 }, "steps_from_proto": { "total": 0.0012550589999591466, "count": 1, "is_parallel": true, "self": 0.000300690000585746, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009543689993734006, "count": 8, "is_parallel": true, "self": 0.0009543689993734006 } } } } } } }, "UnityEnvironment.step": { "total": 2206.6427023588085, "count": 194843, "is_parallel": true, "self": 77.39250522411203, "children": { "UnityEnvironment._generate_step_input": { "total": 51.802898123920386, "count": 194843, "is_parallel": true, "self": 51.802898123920386 }, "communicator.exchange": { "total": 1879.5813172921407, "count": 194843, "is_parallel": true, "self": 1879.5813172921407 }, "steps_from_proto": { "total": 197.86598171863534, "count": 194843, "is_parallel": true, "self": 40.95367453090057, "children": { "_process_rank_one_or_two_observation": { "total": 156.91230718773477, "count": 1558744, "is_parallel": true, "self": 156.91230718773477 } } } } } } } } } } }, "trainer_advance": { "total": 1362.2845368007856, "count": 194844, "self": 3.4505854615017597, "children": { "process_trajectory": { "total": 281.31252649328417, "count": 194844, "self": 280.9420161182825, "children": { "RLTrainer._checkpoint": { "total": 0.37051037500168604, "count": 6, "self": 0.37051037500168604 } } }, "_update_policy": { "total": 1077.5214248459997, "count": 1398, "self": 383.90232618520713, "children": { "TorchPPOOptimizer.update": { "total": 693.6190986607926, "count": 68367, "self": 693.6190986607926 } } } } } } }, "trainer_threads": { "total": 5.59999534743838e-07, "count": 1, "self": 5.59999534743838e-07 }, "TrainerController._save_models": { "total": 0.05774961200040707, "count": 1, "self": 0.0008401560007769149, "children": { "RLTrainer._checkpoint": { "total": 0.056909455999630154, "count": 1, "self": 0.056909455999630154 } } } } } } }