{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5453948974609375, "min": 0.5453948974609375, "max": 1.4915077686309814, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16292.0361328125, "min": 16292.0361328125, "max": 45246.37890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.38538113236427307, "min": -0.0955909714102745, "max": 0.41770029067993164, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 102.89675903320312, "min": -22.94183349609375, "max": 113.19677734375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 16.360816955566406, "min": -0.1930875927209854, "max": 16.360816955566406, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4368.337890625, "min": -50.78203582763672, "max": 4368.337890625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06801365375992775, "min": 0.06521726133429355, "max": 0.07370985161850217, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9521911526389885, "min": 0.4906440676131752, "max": 1.060501630349523, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 29.912240036896296, "min": 0.00019611255523600504, "max": 29.912240036896296, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 418.77136051654816, "min": 0.0027455757733040706, "max": 418.77136051654816, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.7169974277e-06, "min": 7.7169974277e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010803796398780002, "min": 0.00010803796398780002, "max": 0.0035084345305218994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257229999999999, "min": 0.10257229999999999, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360122, "min": 1.3886848, "max": 2.5694781, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026697277000000004, "min": 0.00026697277000000004, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037376187800000006, "min": 0.0037376187800000006, "max": 0.11697086218999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008513377048075199, "min": 0.007972446270287037, "max": 0.3100510239601135, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11918728053569794, "min": 0.11161424964666367, "max": 2.1703572273254395, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 424.6901408450704, "min": 422.54794520547944, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30153.0, "min": 15984.0, "max": 33152.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4406085542270115, "min": -1.0000000521540642, "max": 1.4488225605699323, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 100.84259879589081, "min": -30.9916016086936, "max": 103.15039819478989, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4406085542270115, "min": -1.0000000521540642, "max": 1.4488225605699323, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 100.84259879589081, "min": -30.9916016086936, "max": 103.15039819478989, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03696704734528404, "min": 0.03696704734528404, "max": 6.418480900116265, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.587693314169883, "min": 2.5355656908650417, "max": 102.69569440186024, "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": "1682526146", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1682528392" }, "total": 2246.308129565, "count": 1, "self": 0.7797014669995406, "children": { "run_training.setup": { "total": 0.11689240200007589, "count": 1, "self": 0.11689240200007589 }, "TrainerController.start_learning": { "total": 2245.411535696, "count": 1, "self": 1.5090777700143008, "children": { "TrainerController._reset_env": { "total": 3.909860901000002, "count": 1, "self": 3.909860901000002 }, "TrainerController.advance": { "total": 2239.8390529809853, "count": 63559, "self": 1.5223795160577538, "children": { "env_step": { "total": 1617.4875878039404, "count": 63559, "self": 1506.3141157789323, "children": { "SubprocessEnvManager._take_step": { "total": 110.26800501199705, "count": 63559, "self": 4.80453054196596, "children": { "TorchPolicy.evaluate": { "total": 105.46347447003109, "count": 62557, "self": 105.46347447003109 } } }, "workers": { "total": 0.905467013011048, "count": 63559, "self": 0.0, "children": { "worker_root": { "total": 2239.815159996994, "count": 63559, "is_parallel": true, "self": 851.1071773159645, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001978406000034738, "count": 1, "is_parallel": true, "self": 0.0006393470000602974, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013390589999744407, "count": 8, "is_parallel": true, "self": 0.0013390589999744407 } } }, "UnityEnvironment.step": { "total": 0.05351651900014076, "count": 1, "is_parallel": true, "self": 0.0005735750003168505, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009403719998317683, "count": 1, "is_parallel": true, "self": 0.0009403719998317683 }, "communicator.exchange": { "total": 0.05040523100001337, "count": 1, "is_parallel": true, "self": 0.05040523100001337 }, "steps_from_proto": { "total": 0.001597340999978769, "count": 1, "is_parallel": true, "self": 0.00036294000028647133, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012344009996922978, "count": 8, "is_parallel": true, "self": 0.0012344009996922978 } } } } } } }, "UnityEnvironment.step": { "total": 1388.7079826810298, "count": 63558, "is_parallel": true, "self": 32.64124984892874, "children": { "UnityEnvironment._generate_step_input": { "total": 23.010396003001915, "count": 63558, "is_parallel": true, "self": 23.010396003001915 }, "communicator.exchange": { "total": 1239.0051135500414, "count": 63558, "is_parallel": true, "self": 1239.0051135500414 }, "steps_from_proto": { "total": 94.0512232790577, "count": 63558, "is_parallel": true, "self": 20.470986927843796, "children": { "_process_rank_one_or_two_observation": { "total": 73.5802363512139, "count": 508464, "is_parallel": true, "self": 73.5802363512139 } } } } } } } } } } }, "trainer_advance": { "total": 620.8290856609874, "count": 63559, "self": 2.864323043996592, "children": { "process_trajectory": { "total": 107.19060220599113, "count": 63559, "self": 106.93437550399085, "children": { "RLTrainer._checkpoint": { "total": 0.2562267020002764, "count": 2, "self": 0.2562267020002764 } } }, "_update_policy": { "total": 510.7741604109997, "count": 454, "self": 327.1899827700081, "children": { "TorchPPOOptimizer.update": { "total": 183.58417764099158, "count": 22791, "self": 183.58417764099158 } } } } } } }, "trainer_threads": { "total": 1.3150001905160025e-06, "count": 1, "self": 1.3150001905160025e-06 }, "TrainerController._save_models": { "total": 0.15354272900003707, "count": 1, "self": 0.0020205760001772433, "children": { "RLTrainer._checkpoint": { "total": 0.15152215299985983, "count": 1, "self": 0.15152215299985983 } } } } } } }