{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9872238636016846, "min": 0.9560187458992004, "max": 2.8778398036956787, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9458.591796875, "min": 9458.591796875, "max": 29535.26953125, "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": 12.848539352416992, "min": 0.3894674479961395, "max": 12.848539352416992, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2505.465087890625, "min": 75.55668640136719, "max": 2608.240234375, "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": 0.0658234222386918, "min": 0.06410840705154673, "max": 0.07483835568029248, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2632936889547672, "min": 0.2564336282061869, "max": 0.36804040105483843, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18158820161924644, "min": 0.08535747436975474, "max": 0.28644621153088173, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7263528064769857, "min": 0.341429897479019, "max": 1.4032163976454268, "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": 25.25, "min": 2.409090909090909, "max": 25.6, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1111.0, "min": 106.0, "max": 1408.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.25, "min": 2.409090909090909, "max": 25.6, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1111.0, "min": 106.0, "max": 1408.0, "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": "1687283216", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1687283782" }, "total": 566.8323021299999, "count": 1, "self": 0.9857247919998144, "children": { "run_training.setup": { "total": 0.07776007600000412, "count": 1, "self": 0.07776007600000412 }, "TrainerController.start_learning": { "total": 565.7688172620001, "count": 1, "self": 0.8323848099886391, "children": { "TrainerController._reset_env": { "total": 1.876196400999902, "count": 1, "self": 1.876196400999902 }, "TrainerController.advance": { "total": 562.8125787970114, "count": 18229, "self": 0.38118027601103677, "children": { "env_step": { "total": 562.4313985210003, "count": 18229, "self": 455.14114348301575, "children": { "SubprocessEnvManager._take_step": { "total": 106.90682311400394, "count": 18229, "self": 2.390534069004161, "children": { "TorchPolicy.evaluate": { "total": 104.51628904499978, "count": 18229, "self": 104.51628904499978 } } }, "workers": { "total": 0.38343192398065185, "count": 18229, "self": 0.0, "children": { "worker_root": { "total": 563.4959176320211, "count": 18229, "is_parallel": true, "self": 248.01812399201685, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008198760000027505, "count": 1, "is_parallel": true, "self": 0.0056289919998562254, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025697680001712797, "count": 10, "is_parallel": true, "self": 0.0025697680001712797 } } }, "UnityEnvironment.step": { "total": 0.0795048569999608, "count": 1, "is_parallel": true, "self": 0.0007351539999262968, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004965830000855931, "count": 1, "is_parallel": true, "self": 0.0004965830000855931 }, "communicator.exchange": { "total": 0.07145924700000705, "count": 1, "is_parallel": true, "self": 0.07145924700000705 }, "steps_from_proto": { "total": 0.00681387299994185, "count": 1, "is_parallel": true, "self": 0.00046336200011865003, "children": { "_process_rank_one_or_two_observation": { "total": 0.0063505109998232, "count": 10, "is_parallel": true, "self": 0.0063505109998232 } } } } } } }, "UnityEnvironment.step": { "total": 315.4777936400043, "count": 18228, "is_parallel": true, "self": 13.066838885011407, "children": { "UnityEnvironment._generate_step_input": { "total": 6.8861699049995195, "count": 18228, "is_parallel": true, "self": 6.8861699049995195 }, "communicator.exchange": { "total": 250.81551151999508, "count": 18228, "is_parallel": true, "self": 250.81551151999508 }, "steps_from_proto": { "total": 44.70927332999827, "count": 18228, "is_parallel": true, "self": 8.76677687295603, "children": { "_process_rank_one_or_two_observation": { "total": 35.94249645704224, "count": 182280, "is_parallel": true, "self": 35.94249645704224 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00020572000016727543, "count": 1, "self": 0.00020572000016727543, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 558.1449772630156, "count": 564714, "is_parallel": true, "self": 12.976396341969235, "children": { "process_trajectory": { "total": 298.4114162920465, "count": 564714, "is_parallel": true, "self": 296.78552623704627, "children": { "RLTrainer._checkpoint": { "total": 1.6258900550002409, "count": 4, "is_parallel": true, "self": 1.6258900550002409 } } }, "_update_policy": { "total": 246.75716462899982, "count": 90, "is_parallel": true, "self": 86.25190096499182, "children": { "TorchPPOOptimizer.update": { "total": 160.505263664008, "count": 4587, "is_parallel": true, "self": 160.505263664008 } } } } } } } } }, "TrainerController._save_models": { "total": 0.24745153399999253, "count": 1, "self": 0.0013321760000053473, "children": { "RLTrainer._checkpoint": { "total": 0.2461193579999872, "count": 1, "self": 0.2461193579999872 } } } } } } }