| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.30786994099617004, |
| "min": 0.3035747706890106, |
| "max": 1.4912446737289429, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 9309.9873046875, |
| "min": 9097.5283203125, |
| "max": 45238.3984375, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989960.0, |
| "min": 29952.0, |
| "max": 989960.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989960.0, |
| "min": 29952.0, |
| "max": 989960.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.6741190552711487, |
| "min": -0.12404728680849075, |
| "max": 0.6829549074172974, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 188.0792236328125, |
| "min": -29.399206161499023, |
| "max": 198.16934204101562, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.02373865246772766, |
| "min": 0.008841241709887981, |
| "max": 0.30106568336486816, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 6.62308406829834, |
| "min": 2.484388828277588, |
| "max": 71.35256958007812, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.0679078684827976, |
| "min": 0.06455739669004532, |
| "max": 0.07298525753486458, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9507101587591665, |
| "min": 0.5102156544396594, |
| "max": 1.0677580084302463, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.015231617565968053, |
| "min": 0.0011841848847443024, |
| "max": 0.01725753505130694, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.21324264592355274, |
| "min": 0.015394403501675931, |
| "max": 0.24160549071829712, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.720233140907144e-06, |
| "min": 7.720233140907144e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010808326397270001, |
| "min": 0.00010808326397270001, |
| "max": 0.0035084648305117997, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10257337857142856, |
| "min": 0.10257337857142856, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4360273, |
| "min": 1.3886848, |
| "max": 2.5694882000000003, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002670805192857144, |
| "min": 0.0002670805192857144, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0037391272700000016, |
| "min": 0.0037391272700000016, |
| "max": 0.11697187118000002, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.013592837378382683, |
| "min": 0.013592837378382683, |
| "max": 0.34104791283607483, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.19029971957206726, |
| "min": 0.19029971957206726, |
| "max": 2.3873353004455566, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 282.5925925925926, |
| "min": 270.67543859649123, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30520.0, |
| "min": 15984.0, |
| "max": 33018.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.6618388624930824, |
| "min": -1.0000000521540642, |
| "max": 1.714514831210127, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 179.4785971492529, |
| "min": -29.613001704216003, |
| "max": 193.14219836890697, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.6618388624930824, |
| "min": -1.0000000521540642, |
| "max": 1.714514831210127, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 179.4785971492529, |
| "min": -29.613001704216003, |
| "max": 193.14219836890697, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.03944893315228573, |
| "min": 0.03944893315228573, |
| "max": 6.222614713013172, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 4.260484780446859, |
| "min": 4.260484780446859, |
| "max": 99.56183540821075, |
| "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": "1729578247", |
| "python_version": "3.10.12 (main, Jun 12 2024, 02:25:10) [GCC 12.2.0]", |
| "command_line_arguments": "/home/luser/.pyenv/versions/3.10.12/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": "2.4.1+cu118", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1729579761" |
| }, |
| "total": 1514.490784265101, |
| "count": 1, |
| "self": 0.2753289267420769, |
| "children": { |
| "run_training.setup": { |
| "total": 0.1496268454939127, |
| "count": 1, |
| "self": 0.1496268454939127 |
| }, |
| "TrainerController.start_learning": { |
| "total": 1514.065828492865, |
| "count": 1, |
| "self": 1.5539047848433256, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 1.2428660988807678, |
| "count": 1, |
| "self": 1.2428660988807678 |
| }, |
| "TrainerController.advance": { |
| "total": 1511.2102739587426, |
| "count": 64366, |
| "self": 1.4706240259110928, |
| "children": { |
| "env_step": { |
| "total": 878.23102789931, |
| "count": 64366, |
| "self": 780.5239738970995, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 96.79489367455244, |
| "count": 64366, |
| "self": 3.9262360762804747, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 92.86865759827197, |
| "count": 62553, |
| "self": 92.86865759827197 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.9121603276580572, |
| "count": 64366, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 1511.9636805150658, |
| "count": 64366, |
| "is_parallel": true, |
| "self": 831.167067700997, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0015347693115472794, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004483480006456375, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0010864213109016418, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0010864213109016418 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.027647079899907112, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00038668327033519745, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0002905502915382385, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0002905502915382385 |
| }, |
| "communicator.exchange": { |
| "total": 0.025971844792366028, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.025971844792366028 |
| }, |
| "steps_from_proto": { |
| "total": 0.0009980015456676483, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0002583600580692291, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0007396414875984192, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0007396414875984192 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 680.7966128140688, |
| "count": 64365, |
| "is_parallel": true, |
| "self": 20.55948062799871, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 18.758210077881813, |
| "count": 64365, |
| "is_parallel": true, |
| "self": 18.758210077881813 |
| }, |
| "communicator.exchange": { |
| "total": 577.9006294813007, |
| "count": 64365, |
| "is_parallel": true, |
| "self": 577.9006294813007 |
| }, |
| "steps_from_proto": { |
| "total": 63.57829262688756, |
| "count": 64365, |
| "is_parallel": true, |
| "self": 15.513901114463806, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 48.064391512423754, |
| "count": 514920, |
| "is_parallel": true, |
| "self": 48.064391512423754 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 631.5086220335215, |
| "count": 64366, |
| "self": 2.8546887040138245, |
| "children": { |
| "process_trajectory": { |
| "total": 107.28508945927024, |
| "count": 64366, |
| "self": 107.15276909433305, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.13232036493718624, |
| "count": 2, |
| "self": 0.13232036493718624 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 521.3688438702375, |
| "count": 454, |
| "self": 265.2426653560251, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 256.12617851421237, |
| "count": 22770, |
| "self": 256.12617851421237 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 9.462237358093262e-07, |
| "count": 1, |
| "self": 9.462237358093262e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.058782704174518585, |
| "count": 1, |
| "self": 0.0010871011763811111, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.057695602998137474, |
| "count": 1, |
| "self": 0.057695602998137474 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
