{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.411053866147995, "min": 0.411053866147995, "max": 1.439266562461853, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12403.9619140625, "min": 12403.9619140625, "max": 43661.58984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989931.0, "min": 29952.0, "max": 989931.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989931.0, "min": 29952.0, "max": 989931.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6129696369171143, "min": -0.1162705272436142, "max": 0.6209970116615295, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 172.85743713378906, "min": -28.021196365356445, "max": 172.85743713378906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.031335923820734024, "min": -0.011813916265964508, "max": 0.5913169384002686, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.83673095703125, "min": -3.2724547386169434, "max": 140.14212036132812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07201095225346286, "min": 0.06432939565156656, "max": 0.07349168029103999, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.00815333154848, "min": 0.5011671483068427, "max": 1.1023752043655999, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0134563528020711, "min": 0.0004929824668547105, "max": 0.0173888511621737, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1883889392289954, "min": 0.004436842201692394, "max": 0.24740313333071146, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0002024594753706619, "min": 0.0002024594753706619, "max": 0.00029838354339596195, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0028344326551892666, "min": 0.0020886848037717336, "max": 0.003927270590909833, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16748648095238097, "min": 0.16748648095238097, "max": 0.19946118095238097, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.3448107333333335, "min": 1.3962282666666668, "max": 2.7824956999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.006751899447142856, "min": 0.006751899447142856, "max": 0.009946171977142856, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.09452659225999999, "min": 0.06962320384, "max": 0.13091810765000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010223925113677979, "min": 0.009493397548794746, "max": 0.5476802587509155, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1431349515914917, "min": 0.13290756940841675, "max": 3.833761692047119, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 308.54455445544556, "min": 301.3265306122449, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31163.0, "min": 15984.0, "max": 32569.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6383399803936483, "min": -1.0000000521540642, "max": 1.6578408009847816, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 163.83399803936481, "min": -32.000001668930054, "max": 163.83399803936481, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6383399803936483, "min": -1.0000000521540642, "max": 1.6578408009847816, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 163.83399803936481, "min": -32.000001668930054, "max": 163.83399803936481, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03216302365181036, "min": 0.030718120750472217, "max": 11.846896287053823, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2163023651810363, "min": 2.79769675352145, "max": 189.55034059286118, "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": "1729500444", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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=Pyramids1 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1729504270" }, "total": 3826.5694408010004, "count": 1, "self": 0.6302959190011279, "children": { "run_training.setup": { "total": 0.0758611149999524, "count": 1, "self": 0.0758611149999524 }, "TrainerController.start_learning": { "total": 3825.8632837669993, "count": 1, "self": 3.004285583145247, "children": { "TrainerController._reset_env": { "total": 2.253111907999937, "count": 1, "self": 2.253111907999937 }, "TrainerController.advance": { "total": 3820.469817160854, "count": 64019, "self": 2.9843960680527744, "children": { "env_step": { "total": 2571.655432350898, "count": 64019, "self": 2369.0537317008893, "children": { "SubprocessEnvManager._take_step": { "total": 200.8294860229919, "count": 64019, "self": 8.288255553993167, "children": { "TorchPolicy.evaluate": { "total": 192.54123046899872, "count": 62657, "self": 192.54123046899872 } } }, "workers": { "total": 1.7722146270170924, "count": 64019, "self": 0.0, "children": { "worker_root": { "total": 3815.3734089499785, "count": 64019, "is_parallel": true, "self": 1661.8455435438937, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0033739550001428142, "count": 1, "is_parallel": true, "self": 0.0008332820002578956, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025406729998849187, "count": 8, "is_parallel": true, "self": 0.0025406729998849187 } } }, "UnityEnvironment.step": { "total": 0.13292379699987578, "count": 1, "is_parallel": true, "self": 0.0007499789999201312, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005476950000229408, "count": 1, "is_parallel": true, "self": 0.0005476950000229408 }, "communicator.exchange": { "total": 0.12952019099998324, "count": 1, "is_parallel": true, "self": 0.12952019099998324 }, "steps_from_proto": { "total": 0.002105931999949462, "count": 1, "is_parallel": true, "self": 0.00045312899987948185, "children": { "_process_rank_one_or_two_observation": { "total": 0.00165280300006998, "count": 8, "is_parallel": true, "self": 0.00165280300006998 } } } } } } }, "UnityEnvironment.step": { "total": 2153.527865406085, "count": 64018, "is_parallel": true, "self": 57.70236904218473, "children": { "UnityEnvironment._generate_step_input": { "total": 33.11667569895121, "count": 64018, "is_parallel": true, "self": 33.11667569895121 }, "communicator.exchange": { "total": 1920.9060538890262, "count": 64018, "is_parallel": true, "self": 1920.9060538890262 }, "steps_from_proto": { "total": 141.8027667759227, "count": 64018, "is_parallel": true, "self": 32.11204273758858, "children": { "_process_rank_one_or_two_observation": { "total": 109.69072403833411, "count": 512144, "is_parallel": true, "self": 109.69072403833411 } } } } } } } } } } }, "trainer_advance": { "total": 1245.829988741903, "count": 64019, "self": 5.854841670974565, "children": { "process_trajectory": { "total": 195.2369097329356, "count": 64019, "self": 194.9946395759348, "children": { "RLTrainer._checkpoint": { "total": 0.242270157000803, "count": 2, "self": 0.242270157000803 } } }, "_update_policy": { "total": 1044.7382373379928, "count": 443, "self": 412.02503461300034, "children": { "TorchPPOOptimizer.update": { "total": 632.7132027249925, "count": 22910, "self": 632.7132027249925 } } } } } } }, "trainer_threads": { "total": 2.456000402162317e-06, "count": 1, "self": 2.456000402162317e-06 }, "TrainerController._save_models": { "total": 0.13606665899988002, "count": 1, "self": 0.003119648999927449, "children": { "RLTrainer._checkpoint": { "total": 0.13294700999995257, "count": 1, "self": 0.13294700999995257 } } } } } } }