{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8501556515693665, "min": 0.8501556515693665, "max": 2.8596954345703125, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8117.2861328125, "min": 8117.2861328125, "max": 29286.140625, "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": 12.224271774291992, "min": 0.2826291024684906, "max": 12.224271774291992, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2383.73291015625, "min": 54.830047607421875, "max": 2469.7685546875, "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": 0.069105208001394, "min": 0.06380653350046772, "max": 0.07637967730789016, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.276420832005576, "min": 0.2552261340018709, "max": 0.380291812207753, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18169886673636296, "min": 0.13290783416196777, "max": 0.27259985196824166, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7267954669454518, "min": 0.5316313366478711, "max": 1.3629992598412084, "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": 24.068181818181817, "min": 3.4545454545454546, "max": 24.2, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1059.0, "min": 152.0, "max": 1331.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.068181818181817, "min": 3.4545454545454546, "max": 24.2, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1059.0, "min": 152.0, "max": 1331.0, "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": "1673758031", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673758491" }, "total": 459.798216357, "count": 1, "self": 0.38708323200012273, "children": { "run_training.setup": { "total": 0.11082165999982863, "count": 1, "self": 0.11082165999982863 }, "TrainerController.start_learning": { "total": 459.30031146500005, "count": 1, "self": 0.5453707279996252, "children": { "TrainerController._reset_env": { "total": 9.814386710999997, "count": 1, "self": 9.814386710999997 }, "TrainerController.advance": { "total": 448.8030450460003, "count": 18202, "self": 0.27363328401020226, "children": { "env_step": { "total": 448.5294117619901, "count": 18202, "self": 289.28956116197105, "children": { "SubprocessEnvManager._take_step": { "total": 158.96087602300122, "count": 18202, "self": 1.4669477590064162, "children": { "TorchPolicy.evaluate": { "total": 157.4939282639948, "count": 18202, "self": 35.16867369599936, "children": { "TorchPolicy.sample_actions": { "total": 122.32525456799544, "count": 18202, "self": 122.32525456799544 } } } } }, "workers": { "total": 0.27897457701783424, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 458.0191631999867, "count": 18202, "is_parallel": true, "self": 224.7976107189877, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006745775999888792, "count": 1, "is_parallel": true, "self": 0.00384582499964381, "children": { "_process_rank_one_or_two_observation": { "total": 0.0028999510002449824, "count": 10, "is_parallel": true, "self": 0.0028999510002449824 } } }, "UnityEnvironment.step": { "total": 0.03446334399995976, "count": 1, "is_parallel": true, "self": 0.0005272149999200337, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044167800001559954, "count": 1, "is_parallel": true, "self": 0.00044167800001559954 }, "communicator.exchange": { "total": 0.03144257500002823, "count": 1, "is_parallel": true, "self": 0.03144257500002823 }, "steps_from_proto": { "total": 0.0020518759999959, "count": 1, "is_parallel": true, "self": 0.0005160779999187071, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015357980000771931, "count": 10, "is_parallel": true, "self": 0.0015357980000771931 } } } } } } }, "UnityEnvironment.step": { "total": 233.22155248099898, "count": 18201, "is_parallel": true, "self": 8.887448821981025, "children": { "UnityEnvironment._generate_step_input": { "total": 5.786844506020088, "count": 18201, "is_parallel": true, "self": 5.786844506020088 }, "communicator.exchange": { "total": 182.28431014699117, "count": 18201, "is_parallel": true, "self": 182.28431014699117 }, "steps_from_proto": { "total": 36.26294900600669, "count": 18201, "is_parallel": true, "self": 7.402778000975104, "children": { "_process_rank_one_or_two_observation": { "total": 28.86017100503159, "count": 182010, "is_parallel": true, "self": 28.86017100503159 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.4924000121682184e-05, "count": 1, "self": 4.4924000121682184e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 445.238461050993, "count": 366559, "is_parallel": true, "self": 10.515918836028504, "children": { "process_trajectory": { "total": 254.22660491996544, "count": 366559, "is_parallel": true, "self": 253.39511830796528, "children": { "RLTrainer._checkpoint": { "total": 0.8314866120001625, "count": 4, "is_parallel": true, "self": 0.8314866120001625 } } }, "_update_policy": { "total": 180.49593729499907, "count": 90, "is_parallel": true, "self": 43.72813210999993, "children": { "TorchPPOOptimizer.update": { "total": 136.76780518499913, "count": 4587, "is_parallel": true, "self": 136.76780518499913 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1374640559999989, "count": 1, "self": 0.0011007820000941138, "children": { "RLTrainer._checkpoint": { "total": 0.13636327399990478, "count": 1, "self": 0.13636327399990478 } } } } } } }