{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.739071786403656, "min": 0.739071786403656, "max": 1.4454998970031738, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 22136.677734375, "min": 22136.677734375, "max": 43850.68359375, "count": 3 }, "Pyramids.Step.mean": { "value": 89911.0, "min": 29946.0, "max": 89911.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89911.0, "min": 29946.0, "max": 89911.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0998653993010521, "min": -0.1127043068408966, "max": -0.07943457365036011, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -24.067562103271484, "min": -27.049034118652344, "max": -18.82599449157715, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.17736078798770905, "min": 0.17736078798770905, "max": 0.28578320145606995, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 42.74394989013672, "min": 42.74394989013672, "max": 68.58796691894531, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.070481917966332, "min": 0.0700450923236838, "max": 0.07055446223849861, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.775301097629652, "min": 0.6349901601464875, "max": 0.775301097629652, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0019005925672128901, "min": 0.0006795936407359118, "max": 0.00635632000556461, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.020906518239341792, "min": 0.007475530048095031, "max": 0.05720688005008149, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 4.6610993553939394e-05, "min": 4.6610993553939394e-05, "max": 0.00024898964663308646, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0005127209290933333, "min": 0.0005127209290933333, "max": 0.002240906819697778, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.11553696969696971, "min": 0.11553696969696971, "max": 0.18299654320987654, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.2709066666666669, "min": 1.2709066666666669, "max": 1.6555400000000002, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.0015621432727272726, "min": 0.0015621432727272726, "max": 0.008301354666666667, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.017183576, "min": 0.017183576, "max": 0.074712192, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.10708160698413849, "min": 0.10708160698413849, "max": 0.3998236060142517, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.1778976917266846, "min": 1.1778976917266846, "max": 3.59841251373291, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 988.90625, "min": 962.4117647058823, "max": 999.0, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31645.0, "min": 16361.0, "max": 31968.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8648438029922545, "min": -1.0000000521540642, "max": -0.8457059351836934, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -27.675001695752144, "min": -32.000001668930054, "max": -14.377000898122787, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8648438029922545, "min": -1.0000000521540642, "max": -0.8457059351836934, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -27.675001695752144, "min": -32.000001668930054, "max": -14.377000898122787, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 1.2813467901432887, "min": 1.2813467901432887, "max": 6.793649711153087, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 41.00309728458524, "min": 41.00309728458524, "max": 115.49204508960247, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1767756856", "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/PyramidsRND2.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids_Training1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1767757164" }, "total": 308.50443810399975, "count": 1, "self": 0.8987304379988927, "children": { "run_training.setup": { "total": 0.0379121350006244, "count": 1, "self": 0.0379121350006244 }, "TrainerController.start_learning": { "total": 307.56779553100023, "count": 1, "self": 0.23028390199851856, "children": { "TrainerController._reset_env": { "total": 3.112365932999637, "count": 1, "self": 3.112365932999637 }, "TrainerController.advance": { "total": 304.11618599000303, "count": 5640, "self": 0.23520015898247948, "children": { "env_step": { "total": 194.22835736800334, "count": 5640, "self": 177.21212623802876, "children": { "SubprocessEnvManager._take_step": { "total": 16.887364807993436, "count": 5640, "self": 0.7635568460091235, "children": { "TorchPolicy.evaluate": { "total": 16.123807961984312, "count": 5640, "self": 16.123807961984312 } } }, "workers": { "total": 0.12886632198114967, "count": 5640, "self": 0.0, "children": { "worker_root": { "total": 306.4480607260293, "count": 5640, "is_parallel": true, "self": 147.31205141703504, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026003799994214205, "count": 1, "is_parallel": true, "self": 0.0008689469996170374, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017314329998043831, "count": 8, "is_parallel": true, "self": 0.0017314329998043831 } } }, "UnityEnvironment.step": { "total": 0.18874927400065644, "count": 1, "is_parallel": true, "self": 0.0011363430012352183, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004876650000369409, "count": 1, "is_parallel": true, "self": 0.0004876650000369409 }, "communicator.exchange": { "total": 0.17490177399940876, "count": 1, "is_parallel": true, "self": 0.17490177399940876 }, "steps_from_proto": { "total": 0.012223491999975522, "count": 1, "is_parallel": true, "self": 0.0005006709998269798, "children": { "_process_rank_one_or_two_observation": { "total": 0.011722821000148542, "count": 8, "is_parallel": true, "self": 0.011722821000148542 } } } } } } }, "UnityEnvironment.step": { "total": 159.1360093089943, "count": 5639, "is_parallel": true, "self": 4.570591325059468, "children": { "UnityEnvironment._generate_step_input": { "total": 3.0955321880164774, "count": 5639, "is_parallel": true, "self": 3.0955321880164774 }, "communicator.exchange": { "total": 137.36380916896633, "count": 5639, "is_parallel": true, "self": 137.36380916896633 }, "steps_from_proto": { "total": 14.106076626952017, "count": 5639, "is_parallel": true, "self": 2.8741973519054227, "children": { "_process_rank_one_or_two_observation": { "total": 11.231879275046595, "count": 45112, "is_parallel": true, "self": 11.231879275046595 } } } } } } } } } } }, "trainer_advance": { "total": 109.65262846301721, "count": 5640, "self": 0.3065952489787378, "children": { "process_trajectory": { "total": 15.84585459603477, "count": 5640, "self": 15.84585459603477 }, "_update_policy": { "total": 93.5001786180037, "count": 31, "self": 36.19486772701475, "children": { "TorchPPOOptimizer.update": { "total": 57.30531089098895, "count": 2049, "self": 57.30531089098895 } } } } } } }, "trainer_threads": { "total": 1.0799994925037026e-06, "count": 1, "self": 1.0799994925037026e-06 }, "TrainerController._save_models": { "total": 0.10895862599954853, "count": 1, "self": 0.0020017819997519837, "children": { "RLTrainer._checkpoint": { "total": 0.10695684399979655, "count": 1, "self": 0.10695684399979655 } } } } } } }