| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.15264290571212769, |
| "min": 0.14824354648590088, |
| "max": 1.5362014770507812, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 4564.63330078125, |
| "min": 4452.2275390625, |
| "max": 46602.20703125, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999891.0, |
| "min": 29952.0, |
| "max": 2999891.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999891.0, |
| "min": 29952.0, |
| "max": 2999891.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.7018089890480042, |
| "min": -0.1138012483716011, |
| "max": 0.8274936676025391, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 200.71737670898438, |
| "min": -27.426101684570312, |
| "max": 246.86895751953125, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.010929679498076439, |
| "min": -0.029026180505752563, |
| "max": 0.2527379095554352, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 3.1258883476257324, |
| "min": -7.343623638153076, |
| "max": 60.90983581542969, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.07007433605952323, |
| "min": 0.06340238173738942, |
| "max": 0.07427570199544906, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9810407048333253, |
| "min": 0.483513194690967, |
| "max": 1.1108122498890403, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.016692728976081893, |
| "min": 0.0004845132307979009, |
| "max": 0.01862269539560657, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.2336982056651465, |
| "min": 0.005362080316387025, |
| "max": 0.260717735538492, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.5302423470952365e-06, |
| "min": 1.5302423470952365e-06, |
| "max": 0.00029838354339596195, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 2.1423392859333313e-05, |
| "min": 2.1423392859333313e-05, |
| "max": 0.003883946405351233, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10051004761904762, |
| "min": 0.10051004761904762, |
| "max": 0.19946118095238097, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4071406666666668, |
| "min": 1.3962282666666668, |
| "max": 2.6946487666666665, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 6.0953757142857116e-05, |
| "min": 6.0953757142857116e-05, |
| "max": 0.009946171977142856, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0008533525999999996, |
| "min": 0.0008533525999999996, |
| "max": 0.12947541179, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.006528852973133326, |
| "min": 0.006354281213134527, |
| "max": 0.44610530138015747, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.09140393882989883, |
| "min": 0.0889599397778511, |
| "max": 3.122737169265747, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 245.97272727272727, |
| "min": 226.22307692307692, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 27057.0, |
| "min": 15984.0, |
| "max": 33321.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.6994708916003054, |
| "min": -1.0000000521540642, |
| "max": 1.7719379722378974, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 186.9417980760336, |
| "min": -31.9980016797781, |
| "max": 230.22759766876698, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.6994708916003054, |
| "min": -1.0000000521540642, |
| "max": 1.7719379722378974, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 186.9417980760336, |
| "min": -31.9980016797781, |
| "max": 230.22759766876698, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.016610047667530704, |
| "min": 0.015939703982773074, |
| "max": 9.067096322774887, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 1.8271052434283774, |
| "min": 1.8271052434283774, |
| "max": 145.0735411643982, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1704980400", |
| "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Pyramids Training --no-graphics", |
| "mlagents_version": "1.1.0.dev0", |
| "mlagents_envs_version": "1.1.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.1.2+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1704987979" |
| }, |
| "total": 7579.2098622720005, |
| "count": 1, |
| "self": 0.5000089510003818, |
| "children": { |
| "run_training.setup": { |
| "total": 0.08447227900001053, |
| "count": 1, |
| "self": 0.08447227900001053 |
| }, |
| "TrainerController.start_learning": { |
| "total": 7578.625381042, |
| "count": 1, |
| "self": 4.710864871187368, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 4.286445510000021, |
| "count": 1, |
| "self": 4.286445510000021 |
| }, |
| "TrainerController.advance": { |
| "total": 7569.539156535814, |
| "count": 194199, |
| "self": 5.056888761423579, |
| "children": { |
| "env_step": { |
| "total": 5603.88491842803, |
| "count": 194199, |
| "self": 5183.970999858661, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 417.0539818891125, |
| "count": 194199, |
| "self": 15.055407399132264, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 401.99857448998023, |
| "count": 187548, |
| "self": 401.99857448998023 |
| } |
| } |
| }, |
| "workers": { |
| "total": 2.8599366802557142, |
| "count": 194199, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 7561.010411865854, |
| "count": 194199, |
| "is_parallel": true, |
| "self": 2773.8122937870394, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.005292258000054062, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0035393380001096375, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0017529199999444245, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0017529199999444245 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.0581779239998923, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006854099999600294, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0005166649998500361, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005166649998500361 |
| }, |
| "communicator.exchange": { |
| "total": 0.055128039000010176, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.055128039000010176 |
| }, |
| "steps_from_proto": { |
| "total": 0.0018478100000720588, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00041407300000173564, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014337370000703231, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0014337370000703231 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 4787.198118078814, |
| "count": 194198, |
| "is_parallel": true, |
| "self": 112.87595006926949, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 79.56850473768736, |
| "count": 194198, |
| "is_parallel": true, |
| "self": 79.56850473768736 |
| }, |
| "communicator.exchange": { |
| "total": 4269.562448857002, |
| "count": 194198, |
| "is_parallel": true, |
| "self": 4269.562448857002 |
| }, |
| "steps_from_proto": { |
| "total": 325.19121441485504, |
| "count": 194198, |
| "is_parallel": true, |
| "self": 67.77986581973028, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 257.41134859512476, |
| "count": 1553584, |
| "is_parallel": true, |
| "self": 257.41134859512476 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1960.5973493463612, |
| "count": 194199, |
| "self": 9.302189024512245, |
| "children": { |
| "process_trajectory": { |
| "total": 413.20485653681135, |
| "count": 194199, |
| "self": 412.49199364881133, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.7128628880000178, |
| "count": 6, |
| "self": 0.7128628880000178 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 1538.0903037850376, |
| "count": 1391, |
| "self": 916.6305567821842, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 621.4597470028534, |
| "count": 68268, |
| "self": 621.4597470028534 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.0489984560990706e-06, |
| "count": 1, |
| "self": 1.0489984560990706e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.08891307600060827, |
| "count": 1, |
| "self": 0.0018510070003685541, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.08706206900023972, |
| "count": 1, |
| "self": 0.08706206900023972 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
