{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.013444423675537, "min": 1.0132580995559692, "max": 2.8711605072021484, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9698.6630859375, "min": 9698.6630859375, "max": 29435.138671875, "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": 12.708272933959961, "min": 0.3078102767467499, "max": 12.708272933959961, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2478.11328125, "min": 59.71519088745117, "max": 2586.217529296875, "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.Losses.PolicyLoss.mean": { "value": 0.07342858121082113, "min": 0.059425075267962015, "max": 0.07342858121082113, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2937143248432845, "min": 0.23770030107184806, "max": 0.3670689975249343, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20006442143052233, "min": 0.10245781119310243, "max": 0.30585742968262414, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8002576857220893, "min": 0.40983124477240973, "max": 1.4598720678511787, "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.CumulativeReward.mean": { "value": 24.954545454545453, "min": 3.0, "max": 25.472727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1098.0, "min": 132.0, "max": 1401.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.954545454545453, "min": 3.0, "max": 25.472727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1098.0, "min": 132.0, "max": 1401.0, "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": "1681309703", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1681310141" }, "total": 437.95424797199985, "count": 1, "self": 0.3850201829998241, "children": { "run_training.setup": { "total": 0.10754938300010508, "count": 1, "self": 0.10754938300010508 }, "TrainerController.start_learning": { "total": 437.4616784059999, "count": 1, "self": 0.5464578219896339, "children": { "TrainerController._reset_env": { "total": 3.76707286199985, "count": 1, "self": 3.76707286199985 }, "TrainerController.advance": { "total": 433.01906766301045, "count": 18203, "self": 0.24373884199326312, "children": { "env_step": { "total": 432.7753288210172, "count": 18203, "self": 316.3046258209836, "children": { "SubprocessEnvManager._take_step": { "total": 116.21726271203215, "count": 18203, "self": 1.6261822320361716, "children": { "TorchPolicy.evaluate": { "total": 114.59108047999598, "count": 18203, "self": 114.59108047999598 } } }, "workers": { "total": 0.2534402880014568, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 436.16944148402376, "count": 18203, "is_parallel": true, "self": 202.40097297902707, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005114516000048752, "count": 1, "is_parallel": true, "self": 0.003744088000303236, "children": { "_process_rank_one_or_two_observation": { "total": 0.001370427999745516, "count": 10, "is_parallel": true, "self": 0.001370427999745516 } } }, "UnityEnvironment.step": { "total": 0.04230764899989481, "count": 1, "is_parallel": true, "self": 0.0005759160001161945, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034113600008822687, "count": 1, "is_parallel": true, "self": 0.00034113600008822687 }, "communicator.exchange": { "total": 0.03958081999985552, "count": 1, "is_parallel": true, "self": 0.03958081999985552 }, "steps_from_proto": { "total": 0.0018097769998348667, "count": 1, "is_parallel": true, "self": 0.00038288899963845324, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014268880001964135, "count": 10, "is_parallel": true, "self": 0.0014268880001964135 } } } } } } }, "UnityEnvironment.step": { "total": 233.7684685049967, "count": 18202, "is_parallel": true, "self": 9.613440402034485, "children": { "UnityEnvironment._generate_step_input": { "total": 5.213337588994818, "count": 18202, "is_parallel": true, "self": 5.213337588994818 }, "communicator.exchange": { "total": 188.79638765798813, "count": 18202, "is_parallel": true, "self": 188.79638765798813 }, "steps_from_proto": { "total": 30.145302855979253, "count": 18202, "is_parallel": true, "self": 5.940442814979406, "children": { "_process_rank_one_or_two_observation": { "total": 24.204860040999847, "count": 182020, "is_parallel": true, "self": 24.204860040999847 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014256199983719853, "count": 1, "self": 0.00014256199983719853, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 429.8931341359862, "count": 379984, "is_parallel": true, "self": 9.306430159989759, "children": { "process_trajectory": { "total": 236.61303666899653, "count": 379984, "is_parallel": true, "self": 235.65854448399682, "children": { "RLTrainer._checkpoint": { "total": 0.9544921849997081, "count": 4, "is_parallel": true, "self": 0.9544921849997081 } } }, "_update_policy": { "total": 183.97366730699991, "count": 90, "is_parallel": true, "self": 69.29102518100922, "children": { "TorchPPOOptimizer.update": { "total": 114.6826421259907, "count": 4587, "is_parallel": true, "self": 114.6826421259907 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12893749700015178, "count": 1, "self": 0.0008999240001230646, "children": { "RLTrainer._checkpoint": { "total": 0.12803757300002871, "count": 1, "self": 0.12803757300002871 } } } } } } }