{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5927454829216003, "min": 0.5927454829216003, "max": 1.452760934829712, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17706.4921875, "min": 17706.4921875, "max": 44070.95703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989906.0, "min": 29952.0, "max": 989906.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989906.0, "min": 29952.0, "max": 989906.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.19176076352596283, "min": -0.09941884875297546, "max": 0.21609137952327728, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 48.89899444580078, "min": -23.959941864013672, "max": 54.671119689941406, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.04191944748163223, "min": -0.1827625036239624, "max": 0.3753773868083954, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -10.689458847045898, "min": -46.238914489746094, "max": 88.96443939208984, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06878598744710984, "min": 0.06499108200831175, "max": 0.07537872847369678, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9630038242595378, "min": 0.4941736328336624, "max": 1.0733031960165438, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011718092248881656, "min": 6.754747757999555e-05, "max": 0.016625062556465144, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1640532914843432, "min": 0.0008781172085399422, "max": 0.24937593834697716, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.453683229757138e-06, "min": 7.453683229757138e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010435156521659993, "min": 0.00010435156521659993, "max": 0.0035073488308837992, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248452857142858, "min": 0.10248452857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347834000000002, "min": 1.3886848, "max": 2.5691162, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002582044042857141, "min": 0.0002582044042857141, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036148616599999974, "min": 0.0036148616599999974, "max": 0.11693470838, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010299699380993843, "min": 0.009478597901761532, "max": 0.3961232304573059, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1441957950592041, "min": 0.1327003687620163, "max": 2.772862672805786, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 571.1, "min": 571.1, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28555.0, "min": 15984.0, "max": 33541.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8287239743769169, "min": -1.0000000521540642, "max": 0.86749410205612, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 41.436198718845844, "min": -29.662001617252827, "max": 44.24219920486212, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8287239743769169, "min": -1.0000000521540642, "max": 0.86749410205612, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 41.436198718845844, "min": -29.662001617252827, "max": 44.24219920486212, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06187239394610515, "min": 0.06187239394610515, "max": 7.601030504330993, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0936196973052574, "min": 2.880719599343138, "max": 121.61648806929588, "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": "1687469652", "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": "1687471717" }, "total": 2065.069347914, "count": 1, "self": 0.48867584600020564, "children": { "run_training.setup": { "total": 0.04091304199999968, "count": 1, "self": 0.04091304199999968 }, "TrainerController.start_learning": { "total": 2064.539759026, "count": 1, "self": 1.2579615349945925, "children": { "TrainerController._reset_env": { "total": 4.272525770000016, "count": 1, "self": 4.272525770000016 }, "TrainerController.advance": { "total": 2058.915385005005, "count": 63364, "self": 1.2925478439665312, "children": { "env_step": { "total": 1422.766875102028, "count": 63364, "self": 1316.1694399200198, "children": { "SubprocessEnvManager._take_step": { "total": 105.85858768297976, "count": 63364, "self": 4.572296290018755, "children": { "TorchPolicy.evaluate": { "total": 101.286291392961, "count": 62556, "self": 101.286291392961 } } }, "workers": { "total": 0.7388474990284521, "count": 63364, "self": 0.0, "children": { "worker_root": { "total": 2059.876323041987, "count": 63364, "is_parallel": true, "self": 852.1608897919875, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006677615999990394, "count": 1, "is_parallel": true, "self": 0.005307806999951481, "children": { "_process_rank_one_or_two_observation": { "total": 0.001369809000038913, "count": 8, "is_parallel": true, "self": 0.001369809000038913 } } }, "UnityEnvironment.step": { "total": 0.05084357200001932, "count": 1, "is_parallel": true, "self": 0.000631691000023693, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005054569999742853, "count": 1, "is_parallel": true, "self": 0.0005054569999742853 }, "communicator.exchange": { "total": 0.04784047600003305, "count": 1, "is_parallel": true, "self": 0.04784047600003305 }, "steps_from_proto": { "total": 0.0018659479999882933, "count": 1, "is_parallel": true, "self": 0.0003489590001208853, "children": { "_process_rank_one_or_two_observation": { "total": 0.001516988999867408, "count": 8, "is_parallel": true, "self": 0.001516988999867408 } } } } } } }, "UnityEnvironment.step": { "total": 1207.7154332499993, "count": 63363, "is_parallel": true, "self": 32.647147088046495, "children": { "UnityEnvironment._generate_step_input": { "total": 21.71731862400094, "count": 63363, "is_parallel": true, "self": 21.71731862400094 }, "communicator.exchange": { "total": 1056.2559336779757, "count": 63363, "is_parallel": true, "self": 1056.2559336779757 }, "steps_from_proto": { "total": 97.09503385997624, "count": 63363, "is_parallel": true, "self": 18.576198878972093, "children": { "_process_rank_one_or_two_observation": { "total": 78.51883498100415, "count": 506904, "is_parallel": true, "self": 78.51883498100415 } } } } } } } } } } }, "trainer_advance": { "total": 634.8559620590106, "count": 63364, "self": 2.449839063023319, "children": { "process_trajectory": { "total": 105.17589807798532, "count": 63364, "self": 104.91589518098505, "children": { "RLTrainer._checkpoint": { "total": 0.2600028970002768, "count": 2, "self": 0.2600028970002768 } } }, "_update_policy": { "total": 527.230224918002, "count": 449, "self": 338.990401202005, "children": { "TorchPPOOptimizer.update": { "total": 188.23982371599703, "count": 22833, "self": 188.23982371599703 } } } } } } }, "trainer_threads": { "total": 1.3899998521083035e-06, "count": 1, "self": 1.3899998521083035e-06 }, "TrainerController._save_models": { "total": 0.09388532600041799, "count": 1, "self": 0.001457357000617776, "children": { "RLTrainer._checkpoint": { "total": 0.09242796899980021, "count": 1, "self": 0.09242796899980021 } } } } } } }