{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8409794569015503, "min": 0.5977569818496704, "max": 1.4648127555847168, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 25189.017578125, "min": 17904.017578125, "max": 44436.55859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03576415404677391, "min": -0.168147474527359, "max": -0.006048001814633608, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -8.690689086914062, "min": -39.8509521484375, "max": -1.469664454460144, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.016446761786937714, "min": 0.015186000615358353, "max": 0.5119189023971558, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.996562957763672, "min": 3.6901981830596924, "max": 122.86053466796875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.046404251126833045, "min": 0.04343965201960167, "max": 0.0512588134318191, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.6496595157756626, "min": 0.34889425090070636, "max": 0.7176233880454674, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0027315378738421714, "min": 0.00016747720743630928, "max": 0.00983859278939959, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0382415302337904, "min": 0.0020097264892357113, "max": 0.06887014952579712, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.414897528400003e-06, "min": 7.414897528400003e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010380856539760004, "min": 0.00010380856539760004, "max": 0.0032528858157047998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247160000000001, "min": 0.10247160000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346024000000002, "min": 1.3691136000000002, "max": 2.4018522, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0005040728400000003, "min": 0.0005040728400000003, "max": 0.019676870217142855, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.007057019760000004, "min": 0.007057019760000004, "max": 0.21688061047999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.017543192952871323, "min": 0.017543192952871323, "max": 0.7170633673667908, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2456047087907791, "min": 0.2456047087907791, "max": 5.019443511962891, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 903.0, "min": 875.6969696969697, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30702.0, "min": 15984.0, "max": 33134.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.49170592909350114, "min": -1.0000000521540642, "max": -0.312909131248792, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -16.71800158917904, "min": -32.000001668930054, "max": -10.326001331210136, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.49170592909350114, "min": -1.0000000521540642, "max": -0.312909131248792, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -16.71800158917904, "min": -32.000001668930054, "max": -10.326001331210136, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.16229235304875628, "min": 0.16229235304875628, "max": 10.620858488604426, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.5179400036577135, "min": 5.5179400036577135, "max": 169.93373581767082, "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": "1689191038", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1689193167" }, "total": 2128.7148016630003, "count": 1, "self": 0.4799061830003666, "children": { "run_training.setup": { "total": 0.043691628000033234, "count": 1, "self": 0.043691628000033234 }, "TrainerController.start_learning": { "total": 2128.191203852, "count": 1, "self": 1.7048284780721588, "children": { "TrainerController._reset_env": { "total": 4.172378086999743, "count": 1, "self": 4.172378086999743 }, "TrainerController.advance": { "total": 2122.206610661928, "count": 63202, "self": 1.7325005620396041, "children": { "env_step": { "total": 1554.688638628002, "count": 63202, "self": 1424.7500204250618, "children": { "SubprocessEnvManager._take_step": { "total": 128.97200615100337, "count": 63202, "self": 5.3686703591024525, "children": { "TorchPolicy.evaluate": { "total": 123.60333579190092, "count": 62565, "self": 123.60333579190092 } } }, "workers": { "total": 0.9666120519368633, "count": 63202, "self": 0.0, "children": { "worker_root": { "total": 2122.408931759935, "count": 63202, "is_parallel": true, "self": 827.761396085989, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002103497999996762, "count": 1, "is_parallel": true, "self": 0.0006523439997181413, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014511540002786205, "count": 8, "is_parallel": true, "self": 0.0014511540002786205 } } }, "UnityEnvironment.step": { "total": 0.051914702000431134, "count": 1, "is_parallel": true, "self": 0.0005885840000701137, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005421410000963078, "count": 1, "is_parallel": true, "self": 0.0005421410000963078 }, "communicator.exchange": { "total": 0.04861836800000674, "count": 1, "is_parallel": true, "self": 0.04861836800000674 }, "steps_from_proto": { "total": 0.002165609000257973, "count": 1, "is_parallel": true, "self": 0.00041024500023922883, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017553640000187443, "count": 8, "is_parallel": true, "self": 0.0017553640000187443 } } } } } } }, "UnityEnvironment.step": { "total": 1294.647535673946, "count": 63201, "is_parallel": true, "self": 36.29670716719602, "children": { "UnityEnvironment._generate_step_input": { "total": 26.5234780589617, "count": 63201, "is_parallel": true, "self": 26.5234780589617 }, "communicator.exchange": { "total": 1112.1258844318286, "count": 63201, "is_parallel": true, "self": 1112.1258844318286 }, "steps_from_proto": { "total": 119.7014660159598, "count": 63201, "is_parallel": true, "self": 23.682647248981993, "children": { "_process_rank_one_or_two_observation": { "total": 96.0188187669778, "count": 505608, "is_parallel": true, "self": 96.0188187669778 } } } } } } } } } } }, "trainer_advance": { "total": 565.7854714718865, "count": 63202, "self": 2.969392996890747, "children": { "process_trajectory": { "total": 122.23225650999575, "count": 63202, "self": 122.00311516599595, "children": { "RLTrainer._checkpoint": { "total": 0.22914134399979957, "count": 2, "self": 0.22914134399979957 } } }, "_update_policy": { "total": 440.58382196499997, "count": 439, "self": 330.2906470909488, "children": { "TorchPPOOptimizer.update": { "total": 110.29317487405115, "count": 11298, "self": 110.29317487405115 } } } } } } }, "trainer_threads": { "total": 1.2760001482092775e-06, "count": 1, "self": 1.2760001482092775e-06 }, "TrainerController._save_models": { "total": 0.10738534899974184, "count": 1, "self": 0.0015804989998287056, "children": { "RLTrainer._checkpoint": { "total": 0.10580484999991313, "count": 1, "self": 0.10580484999991313 } } } } } } }