{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1524684578180313, "min": 0.1489453911781311, "max": 1.4680671691894531, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4574.0537109375, "min": 4461.21240234375, "max": 44535.28515625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999892.0, "min": 29952.0, "max": 2999892.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999892.0, "min": 29952.0, "max": 2999892.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8204796314239502, "min": -0.18657706677913666, "max": 0.8695836067199707, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 249.42581176757812, "min": -44.21876525878906, "max": 266.09259033203125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017491644248366356, "min": -0.002176961163058877, "max": 0.47751331329345703, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.317460060119629, "min": -0.6139030456542969, "max": 113.170654296875, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06600798236156281, "min": 0.06300524752190877, "max": 0.07340456436097535, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9241117530618794, "min": 0.4942299785895672, "max": 1.1010684654146303, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014810037991819193, "min": 6.814774438781174e-05, "max": 0.017102957610318083, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2073405318854687, "min": 0.0008859206770415525, "max": 0.24047628211944053, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5420280574523783e-06, "min": 1.5420280574523783e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1588392804333298e-05, "min": 2.1588392804333298e-05, "max": 0.003968991977002699, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10051397619047618, "min": 0.10051397619047618, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4071956666666665, "min": 1.3897045333333333, "max": 2.7525463000000006, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.134622142857135e-05, "min": 6.134622142857135e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008588470999999989, "min": 0.0008588470999999989, "max": 0.13230743027, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00636307755485177, "min": 0.005929993931204081, "max": 0.5823926329612732, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08908308297395706, "min": 0.0830199122428894, "max": 4.076748371124268, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 224.59558823529412, "min": 216.87755102040816, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30545.0, "min": 15984.0, "max": 34438.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7754043960834252, "min": -1.0000000521540642, "max": 1.7754043960834252, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 241.4549978673458, "min": -32.000001668930054, "max": 258.1185979992151, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7754043960834252, "min": -1.0000000521540642, "max": 1.7754043960834252, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 241.4549978673458, "min": -32.000001668930054, "max": 258.1185979992151, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014849673129206434, "min": 0.014819062693582854, "max": 11.753824390470982, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.019555545572075, "min": 1.8581851304588781, "max": 188.0611902475357, "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": "1700131498", "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/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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700138874" }, "total": 7376.036715425, "count": 1, "self": 0.42636976599987975, "children": { "run_training.setup": { "total": 0.04719481899996936, "count": 1, "self": 0.04719481899996936 }, "TrainerController.start_learning": { "total": 7375.56315084, "count": 1, "self": 4.050436751952475, "children": { "TrainerController._reset_env": { "total": 3.3954388129999415, "count": 1, "self": 3.3954388129999415 }, "TrainerController.advance": { "total": 7368.039538942048, "count": 195009, "self": 4.305748044085703, "children": { "env_step": { "total": 5486.2269235829435, "count": 195009, "self": 5096.032604958755, "children": { "SubprocessEnvManager._take_step": { "total": 387.65070928120326, "count": 195009, "self": 13.832868976288978, "children": { "TorchPolicy.evaluate": { "total": 373.8178403049143, "count": 187556, "self": 373.8178403049143 } } }, "workers": { "total": 2.543609342985974, "count": 195009, "self": 0.0, "children": { "worker_root": { "total": 7361.19645619097, "count": 195009, "is_parallel": true, "self": 2632.174387399933, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019491089999519318, "count": 1, "is_parallel": true, "self": 0.0006271339998420444, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013219750001098873, "count": 8, "is_parallel": true, "self": 0.0013219750001098873 } } }, "UnityEnvironment.step": { "total": 0.04869354300001305, "count": 1, "is_parallel": true, "self": 0.0005790620001562274, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004592599999568847, "count": 1, "is_parallel": true, "self": 0.0004592599999568847 }, "communicator.exchange": { "total": 0.04597814299995662, "count": 1, "is_parallel": true, "self": 0.04597814299995662 }, "steps_from_proto": { "total": 0.0016770779999433216, "count": 1, "is_parallel": true, "self": 0.0003584520000003977, "children": { "_process_rank_one_or_two_observation": { "total": 0.001318625999942924, "count": 8, "is_parallel": true, "self": 0.001318625999942924 } } } } } } }, "UnityEnvironment.step": { "total": 4729.022068791037, "count": 195008, "is_parallel": true, "self": 102.07187147093373, "children": { "UnityEnvironment._generate_step_input": { "total": 72.29364314100746, "count": 195008, "is_parallel": true, "self": 72.29364314100746 }, "communicator.exchange": { "total": 4258.652781626951, "count": 195008, "is_parallel": true, "self": 4258.652781626951 }, "steps_from_proto": { "total": 296.0037725521454, "count": 195008, "is_parallel": true, "self": 60.9055021962771, "children": { "_process_rank_one_or_two_observation": { "total": 235.0982703558683, "count": 1560064, "is_parallel": true, "self": 235.0982703558683 } } } } } } } } } } }, "trainer_advance": { "total": 1877.506867315019, "count": 195009, "self": 8.13225329515899, "children": { "process_trajectory": { "total": 380.0483941018763, "count": 195009, "self": 379.4144600588761, "children": { "RLTrainer._checkpoint": { "total": 0.6339340430001812, "count": 6, "self": 0.6339340430001812 } } }, "_update_policy": { "total": 1489.3262199179837, "count": 1393, "self": 889.8790561909059, "children": { "TorchPPOOptimizer.update": { "total": 599.4471637270779, "count": 68403, "self": 599.4471637270779 } } } } } } }, "trainer_threads": { "total": 1.041999894368928e-06, "count": 1, "self": 1.041999894368928e-06 }, "TrainerController._save_models": { "total": 0.07773529099995358, "count": 1, "self": 0.0014272089993028203, "children": { "RLTrainer._checkpoint": { "total": 0.07630808200065076, "count": 1, "self": 0.07630808200065076 } } } } } } }