{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1493377685546875, "min": 1.1493377685546875, "max": 2.864180564880371, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 57347.35546875, "min": 57347.35546875, "max": 144675.484375, "count": 10 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 49936.0, "max": 499976.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 49936.0, "max": 499976.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.845760345458984, "min": 0.3540566861629486, "max": 12.845760345458984, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 12884.2978515625, "min": 351.2242431640625, "max": 12884.2978515625, "count": 10 }, "SnowballTarget.Policy.CuriosityValueEstimate.mean": { "value": 0.8443097472190857, "min": 0.21610280871391296, "max": 1.0515366792678833, "count": 10 }, "SnowballTarget.Policy.CuriosityValueEstimate.sum": { "value": 846.8426513671875, "min": 214.37399291992188, "max": 1044.1759033203125, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 50347.0, "min": 48158.0, "max": 50347.0, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.893280632411066, "min": 3.855371900826446, "max": 25.893280632411066, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 6551.0, "min": 933.0, "max": 6551.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.893280632411066, "min": 3.855371900826446, "max": 25.893280632411066, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 6551.0, "min": 933.0, "max": 6551.0, "count": 10 }, "SnowballTarget.Policy.CuriosityReward.mean": { "value": 1.624363026246723, "min": 1.624363026246723, "max": 2.892317029639832, "count": 10 }, "SnowballTarget.Policy.CuriosityReward.sum": { "value": 410.9638456404209, "min": 410.9638456404209, "max": 699.9407211728394, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.022228808685273785, "min": 0.0222080560298006, "max": 0.026353130527180232, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.08891523474109514, "min": 0.08891523474109514, "max": 0.12910080968249532, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.13977829820166032, "min": 0.07806220607211192, "max": 0.19508210450410843, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5591131928066413, "min": 0.3122488242884477, "max": 0.9754105225205422, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.4576495141199999e-05, "min": 1.4576495141199999e-05, "max": 0.0002841864052712, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.8305980564799996e-05, "min": 5.8305980564799996e-05, "max": 0.0012797184734271998, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1048588, "min": 0.1048588, "max": 0.19472879999999998, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4194352, "min": 0.4194352, "max": 0.9265728000000001, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00025245412000000005, "min": 0.00025245412000000005, "max": 0.004736967120000001, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0010098164800000002, "min": 0.0010098164800000002, "max": 0.02133598272, "count": 10 }, "SnowballTarget.Losses.CuriosityForwardLoss.mean": { "value": 0.04066641284152865, "min": 0.04066641284152865, "max": 0.15649448223412038, "count": 10 }, "SnowballTarget.Losses.CuriosityForwardLoss.sum": { "value": 0.1626656513661146, "min": 0.1626656513661146, "max": 0.6259779289364815, "count": 10 }, "SnowballTarget.Losses.CuriosityInverseLoss.mean": { "value": 1.054714846611023, "min": 1.054714846611023, "max": 2.801060312986374, "count": 10 }, "SnowballTarget.Losses.CuriosityInverseLoss.sum": { "value": 4.218859386444092, "min": 4.218859386444092, "max": 12.449160003662112, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1711530713", "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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget3 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711531767" }, "total": 1053.6621658160002, "count": 1, "self": 0.42601278500069384, "children": { "run_training.setup": { "total": 0.06015482199973121, "count": 1, "self": 0.06015482199973121 }, "TrainerController.start_learning": { "total": 1053.1759982089998, "count": 1, "self": 0.8691430139365366, "children": { "TrainerController._reset_env": { "total": 2.0402573049996136, "count": 1, "self": 2.0402573049996136 }, "TrainerController.advance": { "total": 1050.1352405880639, "count": 45464, "self": 0.9238774870291309, "children": { "env_step": { "total": 752.7561935750673, "count": 45464, "self": 584.8651935689213, "children": { "SubprocessEnvManager._take_step": { "total": 167.33226991003266, "count": 45464, "self": 3.134988525036988, "children": { "TorchPolicy.evaluate": { "total": 164.19728138499568, "count": 45464, "self": 164.19728138499568 } } }, "workers": { "total": 0.5587300961133224, "count": 45464, "self": 0.0, "children": { "worker_root": { "total": 1049.6666539140938, "count": 45464, "is_parallel": true, "self": 537.8826951320802, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022327749998112267, "count": 1, "is_parallel": true, "self": 0.0006461329994635889, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015866420003476378, "count": 10, "is_parallel": true, "self": 0.0015866420003476378 } } }, "UnityEnvironment.step": { "total": 0.034909802000129275, "count": 1, "is_parallel": true, "self": 0.0006885730003887147, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000443045999872993, "count": 1, "is_parallel": true, "self": 0.000443045999872993 }, "communicator.exchange": { "total": 0.03193026799999643, "count": 1, "is_parallel": true, "self": 0.03193026799999643 }, "steps_from_proto": { "total": 0.0018479149998711364, "count": 1, "is_parallel": true, "self": 0.000360121000539948, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014877939993311884, "count": 10, "is_parallel": true, "self": 0.0014877939993311884 } } } } } } }, "UnityEnvironment.step": { "total": 511.78395878201354, "count": 45463, "is_parallel": true, "self": 25.870365160052643, "children": { "UnityEnvironment._generate_step_input": { "total": 13.876963266005987, "count": 45463, "is_parallel": true, "self": 13.876963266005987 }, "communicator.exchange": { "total": 390.81473614399374, "count": 45463, "is_parallel": true, "self": 390.81473614399374 }, "steps_from_proto": { "total": 81.22189421196117, "count": 45463, "is_parallel": true, "self": 14.647346818277128, "children": { "_process_rank_one_or_two_observation": { "total": 66.57454739368404, "count": 454630, "is_parallel": true, "self": 66.57454739368404 } } } } } } } } } } }, "trainer_advance": { "total": 296.45516952596745, "count": 45464, "self": 1.0763309329308868, "children": { "process_trajectory": { "total": 119.15690446203689, "count": 45464, "self": 119.00658910103766, "children": { "RLTrainer._checkpoint": { "total": 0.1503153609992296, "count": 1, "self": 0.1503153609992296 } } }, "_update_policy": { "total": 176.22193413099967, "count": 47, "self": 146.0050128549974, "children": { "TorchPPOOptimizer.update": { "total": 30.216921276002267, "count": 1410, "self": 30.216921276002267 } } } } } } }, "trainer_threads": { "total": 8.010001693037339e-07, "count": 1, "self": 8.010001693037339e-07 }, "TrainerController._save_models": { "total": 0.13135650099957275, "count": 1, "self": 0.0007333689991355641, "children": { "RLTrainer._checkpoint": { "total": 0.13062313200043718, "count": 1, "self": 0.13062313200043718 } } } } } } }