{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.424765020608902, "min": 0.4119285047054291, "max": 1.4867548942565918, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12715.765625, "min": 12305.1279296875, "max": 45102.1953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989941.0, "min": 29952.0, "max": 989941.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989941.0, "min": 29952.0, "max": 989941.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.372586727142334, "min": -0.08464962244033813, "max": 0.3766438364982605, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 97.61772155761719, "min": -20.400558471679688, "max": 99.05732727050781, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.02683073841035366, "min": -0.04151100292801857, "max": 0.2518584728240967, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -7.029653549194336, "min": -10.875883102416992, "max": 60.69789123535156, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06701819690143955, "min": 0.06646167997637516, "max": 0.07406384431660272, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9382547566201537, "min": 0.4792750939809123, "max": 1.069038350796487, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014648039794077963, "min": 0.0006776132597608893, "max": 0.014648039794077963, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2050725571170915, "min": 0.00948658563665245, "max": 0.2050725571170915, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.474040365828574e-06, "min": 7.474040365828574e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010463656512160003, "min": 0.00010463656512160003, "max": 0.0037580728473090995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249131428571431, "min": 0.10249131428571431, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348784000000003, "min": 1.3886848, "max": 2.6526909000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025888229714285724, "min": 0.00025888229714285724, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036243521600000015, "min": 0.0036243521600000015, "max": 0.12528382090999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00896556954830885, "min": 0.008718709461390972, "max": 0.40441542863845825, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12551797926425934, "min": 0.12551797926425934, "max": 2.8309080600738525, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 458.5692307692308, "min": 458.5692307692308, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29807.0, "min": 15984.0, "max": 33786.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.32599381930553, "min": -1.0000000521540642, "max": 1.333065596758388, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 86.18959825485945, "min": -28.595801651477814, "max": 90.5663985311985, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.32599381930553, "min": -1.0000000521540642, "max": 1.333065596758388, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 86.18959825485945, "min": -28.595801651477814, "max": 90.5663985311985, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.043383853558267356, "min": 0.043383853558267356, "max": 7.7885274440050125, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8199504812873784, "min": 2.706364073557779, "max": 124.6164391040802, "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": "1721297804", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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=PyramidsTraining --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1721301009" }, "total": 3204.545077333, "count": 1, "self": 0.8905755549994865, "children": { "run_training.setup": { "total": 0.08177284700013843, "count": 1, "self": 0.08177284700013843 }, "TrainerController.start_learning": { "total": 3203.5727289310003, "count": 1, "self": 2.301829833972988, "children": { "TrainerController._reset_env": { "total": 3.5984146050000163, "count": 1, "self": 3.5984146050000163 }, "TrainerController.advance": { "total": 3197.518689746026, "count": 63679, "self": 2.701033685884795, "children": { "env_step": { "total": 2107.1204945139843, "count": 63679, "self": 1938.9497795951052, "children": { "SubprocessEnvManager._take_step": { "total": 166.71043354496396, "count": 63679, "self": 7.168764090063178, "children": { "TorchPolicy.evaluate": { "total": 159.54166945490078, "count": 62560, "self": 159.54166945490078 } } }, "workers": { "total": 1.4602813739152225, "count": 63679, "self": 0.0, "children": { "worker_root": { "total": 3196.057964891002, "count": 63679, "is_parallel": true, "self": 1449.480650987061, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003176782000082312, "count": 1, "is_parallel": true, "self": 0.0010249880010633206, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021517939990189916, "count": 8, "is_parallel": true, "self": 0.0021517939990189916 } } }, "UnityEnvironment.step": { "total": 0.06214936800006399, "count": 1, "is_parallel": true, "self": 0.0007350860005317372, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005210129997976765, "count": 1, "is_parallel": true, "self": 0.0005210129997976765 }, "communicator.exchange": { "total": 0.0589355459997023, "count": 1, "is_parallel": true, "self": 0.0589355459997023 }, "steps_from_proto": { "total": 0.0019577230000322743, "count": 1, "is_parallel": true, "self": 0.00040338400003747665, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015543389999947976, "count": 8, "is_parallel": true, "self": 0.0015543389999947976 } } } } } } }, "UnityEnvironment.step": { "total": 1746.577313903941, "count": 63678, "is_parallel": true, "self": 50.599908572736695, "children": { "UnityEnvironment._generate_step_input": { "total": 31.61226987805867, "count": 63678, "is_parallel": true, "self": 31.61226987805867 }, "communicator.exchange": { "total": 1535.3427571131224, "count": 63678, "is_parallel": true, "self": 1535.3427571131224 }, "steps_from_proto": { "total": 129.02237834002335, "count": 63678, "is_parallel": true, "self": 27.94679848288615, "children": { "_process_rank_one_or_two_observation": { "total": 101.0755798571372, "count": 509424, "is_parallel": true, "self": 101.0755798571372 } } } } } } } } } } }, "trainer_advance": { "total": 1087.697161546157, "count": 63679, "self": 4.641892049107355, "children": { "process_trajectory": { "total": 164.08552729404437, "count": 63679, "self": 163.79184999504469, "children": { "RLTrainer._checkpoint": { "total": 0.29367729899968253, "count": 2, "self": 0.29367729899968253 } } }, "_update_policy": { "total": 918.9697422030054, "count": 458, "self": 381.00157603995285, "children": { "TorchPPOOptimizer.update": { "total": 537.9681661630525, "count": 22782, "self": 537.9681661630525 } } } } } } }, "trainer_threads": { "total": 1.6200001482502557e-06, "count": 1, "self": 1.6200001482502557e-06 }, "TrainerController._save_models": { "total": 0.1537931260008918, "count": 1, "self": 0.005841875000442087, "children": { "RLTrainer._checkpoint": { "total": 0.1479512510004497, "count": 1, "self": 0.1479512510004497 } } } } } } }