{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2825707495212555, "min": 0.22387881577014923, "max": 1.484754204750061, "count": 59 }, "Pyramids.Policy.Entropy.sum": { "value": 8454.5166015625, "min": 6594.57421875, "max": 45041.50390625, "count": 59 }, "Pyramids.Step.mean": { "value": 1769994.0, "min": 29960.0, "max": 1769994.0, "count": 59 }, "Pyramids.Step.sum": { "value": 1769994.0, "min": 29960.0, "max": 1769994.0, "count": 59 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7614902257919312, "min": -0.1332208663225174, "max": 0.7614902257919312, "count": 59 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 220.0706787109375, "min": -31.706565856933594, "max": 220.0706787109375, "count": 59 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008222896605730057, "min": -0.020413419231772423, "max": 0.2675229012966156, "count": 59 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.3764171600341797, "min": -5.674930572509766, "max": 63.67045211791992, "count": 59 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06905149729711758, "min": 0.06453335709686922, "max": 0.07443348903256093, "count": 59 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9667209621596462, "min": 0.5084016409745419, "max": 1.1031234240314614, "count": 59 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014394447526207105, "min": 0.00015312714120624415, "max": 0.01707035907297506, "count": 59 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20152226536689946, "min": 0.001990652835681174, "max": 0.23898502702165086, "count": 59 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00012445359422977382, "min": 0.00012445359422977382, "max": 0.00029841268624339047, "count": 59 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0017423503192168337, "min": 0.0017423503192168337, "max": 0.003969265876911399, "count": 59 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1414845119047619, "min": 0.1414845119047619, "max": 0.19947089523809525, "count": 59 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.9807831666666669, "min": 1.3962962666666667, "max": 2.7374601333333337, "count": 59 }, "Pyramids.Policy.Beta.mean": { "value": 0.004154302739285715, "min": 0.004154302739285715, "max": 0.009947142434285712, "count": 59 }, "Pyramids.Policy.Beta.sum": { "value": 0.058160238350000004, "min": 0.058160238350000004, "max": 0.13231655114000002, "count": 59 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004645480774343014, "min": 0.004645480774343014, "max": 0.32575327157974243, "count": 59 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06503672897815704, "min": 0.06503672897815704, "max": 2.280272960662842, "count": 59 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 254.44827586206895, "min": 254.44827586206895, "max": 999.0, "count": 59 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29516.0, "min": 16631.0, "max": 33038.0, "count": 59 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7460869426312653, "min": -0.9999500517733395, "max": 1.7460869426312653, "count": 59 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 200.79999840259552, "min": -31.998401656746864, "max": 200.79999840259552, "count": 59 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7460869426312653, "min": -0.9999500517733395, "max": 1.7460869426312653, "count": 59 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 200.79999840259552, "min": -31.998401656746864, "max": 200.79999840259552, "count": 59 }, "Pyramids.Policy.RndReward.mean": { "value": 0.012327873384049821, "min": 0.012327873384049821, "max": 6.094792645643739, "count": 59 }, "Pyramids.Policy.RndReward.sum": { "value": 1.4177054391657293, "min": 1.4177054391657293, "max": 103.61147497594357, "count": 59 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 59 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 59 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1753339545", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1753343659" }, "total": 4113.742559406999, "count": 1, "self": 0.47327715199935483, "children": { "run_training.setup": { "total": 0.01992553499985661, "count": 1, "self": 0.01992553499985661 }, "TrainerController.start_learning": { "total": 4113.24935672, "count": 1, "self": 2.4142092620459152, "children": { "TrainerController._reset_env": { "total": 3.008447115999843, "count": 1, "self": 3.008447115999843 }, "TrainerController.advance": { "total": 4107.820897018954, "count": 115203, "self": 2.540927285998805, "children": { "env_step": { "total": 2925.440198642833, "count": 115203, "self": 2657.7397333827325, "children": { "SubprocessEnvManager._take_step": { "total": 266.23729499216506, "count": 115203, "self": 8.38697985921408, "children": { "TorchPolicy.evaluate": { "total": 257.850315132951, "count": 112075, "self": 257.850315132951 } } }, "workers": { "total": 1.4631702679353111, "count": 115203, "self": 0.0, "children": { "worker_root": { "total": 4103.088902737075, "count": 115203, "is_parallel": true, "self": 1648.6119731492622, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023924530000840605, "count": 1, "is_parallel": true, "self": 0.0007148569998207677, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016775960002632928, "count": 8, "is_parallel": true, "self": 0.0016775960002632928 } } }, "UnityEnvironment.step": { "total": 0.049610346999998, "count": 1, "is_parallel": true, "self": 0.0005626020001727738, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004392669998196652, "count": 1, "is_parallel": true, "self": 0.0004392669998196652 }, "communicator.exchange": { "total": 0.047033207999902515, "count": 1, "is_parallel": true, "self": 0.047033207999902515 }, "steps_from_proto": { "total": 0.0015752700001030462, "count": 1, "is_parallel": true, "self": 0.00033907800116139697, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012361919989416492, "count": 8, "is_parallel": true, "self": 0.0012361919989416492 } } } } } } }, "UnityEnvironment.step": { "total": 2454.4769295878127, "count": 115202, "is_parallel": true, "self": 57.1542970005944, "children": { "UnityEnvironment._generate_step_input": { "total": 40.63059446599573, "count": 115202, "is_parallel": true, "self": 40.63059446599573 }, "communicator.exchange": { "total": 2185.2097238491533, "count": 115202, "is_parallel": true, "self": 2185.2097238491533 }, "steps_from_proto": { "total": 171.4823142720693, "count": 115202, "is_parallel": true, "self": 34.66322732030949, "children": { "_process_rank_one_or_two_observation": { "total": 136.8190869517598, "count": 921616, "is_parallel": true, "self": 136.8190869517598 } } } } } } } } } } }, "trainer_advance": { "total": 1179.8397710901222, "count": 115203, "self": 4.873459739307691, "children": { "process_trajectory": { "total": 228.35865926081124, "count": 115203, "self": 228.0034875868114, "children": { "RLTrainer._checkpoint": { "total": 0.3551716739998483, "count": 3, "self": 0.3551716739998483 } } }, "_update_policy": { "total": 946.6076520900033, "count": 818, "self": 526.9888896229922, "children": { "TorchPPOOptimizer.update": { "total": 419.61876246701104, "count": 40892, "self": 419.61876246701104 } } } } } } }, "trainer_threads": { "total": 1.4950001059332862e-06, "count": 1, "self": 1.4950001059332862e-06 }, "TrainerController._save_models": { "total": 0.005801827999675879, "count": 1, "self": 2.7181999939784873e-05, "children": { "RLTrainer._checkpoint": { "total": 0.005774645999736094, "count": 1, "self": 0.005774645999736094 } } } } } } }