{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7373868823051453, "min": 0.7340883612632751, "max": 2.8421597480773926, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7008.125, "min": 7008.125, "max": 29012.765625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.985459327697754, "min": 0.38856640458106995, "max": 12.985459327697754, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2532.16455078125, "min": 75.38188171386719, "max": 2623.66748046875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06164345767590966, "min": 0.05558276152299311, "max": 0.07429929476176553, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24657383070363864, "min": 0.22233104609197243, "max": 0.36631769858935265, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19466212442984768, "min": 0.1259216615934765, "max": 0.2737647503906605, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7786484977193907, "min": 0.503686646373906, "max": 1.3609047619735493, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.931818181818183, "min": 3.590909090909091, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1141.0, "min": 158.0, "max": 1392.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.931818181818183, "min": 3.590909090909091, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1141.0, "min": 158.0, "max": 1392.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1752790110", "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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1752790599" }, "total": 489.4781623570002, "count": 1, "self": 0.4437289030001921, "children": { "run_training.setup": { "total": 0.03187710000020161, "count": 1, "self": 0.03187710000020161 }, "TrainerController.start_learning": { "total": 489.0025563539998, "count": 1, "self": 0.48707054202168365, "children": { "TrainerController._reset_env": { "total": 3.8841796859996975, "count": 1, "self": 3.8841796859996975 }, "TrainerController.advance": { "total": 484.54866339797854, "count": 18192, "self": 0.5110820059740036, "children": { "env_step": { "total": 352.4757125729875, "count": 18192, "self": 271.8367434750244, "children": { "SubprocessEnvManager._take_step": { "total": 80.34417348497436, "count": 18192, "self": 1.534352719018898, "children": { "TorchPolicy.evaluate": { "total": 78.80982076595546, "count": 18192, "self": 78.80982076595546 } } }, "workers": { "total": 0.29479561298876433, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 487.25225851604773, "count": 18192, "is_parallel": true, "self": 250.22902674508305, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006034133999946789, "count": 1, "is_parallel": true, "self": 0.0036490369989223836, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023850970010244055, "count": 10, "is_parallel": true, "self": 0.0023850970010244055 } } }, "UnityEnvironment.step": { "total": 0.04037335200018788, "count": 1, "is_parallel": true, "self": 0.0006342820006466354, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004241619999447721, "count": 1, "is_parallel": true, "self": 0.0004241619999447721 }, "communicator.exchange": { "total": 0.03737485899955573, "count": 1, "is_parallel": true, "self": 0.03737485899955573 }, "steps_from_proto": { "total": 0.0019400490000407444, "count": 1, "is_parallel": true, "self": 0.00039159299922175705, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015484560008189874, "count": 10, "is_parallel": true, "self": 0.0015484560008189874 } } } } } } }, "UnityEnvironment.step": { "total": 237.02323177096468, "count": 18191, "is_parallel": true, "self": 11.142855818837688, "children": { "UnityEnvironment._generate_step_input": { "total": 5.978650652063152, "count": 18191, "is_parallel": true, "self": 5.978650652063152 }, "communicator.exchange": { "total": 184.93257201202186, "count": 18191, "is_parallel": true, "self": 184.93257201202186 }, "steps_from_proto": { "total": 34.96915328804198, "count": 18191, "is_parallel": true, "self": 6.5944599639519765, "children": { "_process_rank_one_or_two_observation": { "total": 28.374693324090003, "count": 181910, "is_parallel": true, "self": 28.374693324090003 } } } } } } } } } } }, "trainer_advance": { "total": 131.56186881901704, "count": 18192, "self": 0.6168674060609192, "children": { "process_trajectory": { "total": 28.302528668963078, "count": 18192, "self": 27.823561693963256, "children": { "RLTrainer._checkpoint": { "total": 0.4789669749998211, "count": 4, "self": 0.4789669749998211 } } }, "_update_policy": { "total": 102.64247274399304, "count": 90, "self": 41.70085176600378, "children": { "TorchPPOOptimizer.update": { "total": 60.94162097798926, "count": 4587, "self": 60.94162097798926 } } } } } } }, "trainer_threads": { "total": 8.789997991698328e-07, "count": 1, "self": 8.789997991698328e-07 }, "TrainerController._save_models": { "total": 0.08264184900008331, "count": 1, "self": 0.0008913500000744534, "children": { "RLTrainer._checkpoint": { "total": 0.08175049900000886, "count": 1, "self": 0.08175049900000886 } } } } } } }