{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.4142709970474243, "min": 1.4142709970474243, "max": 2.886683940887451, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 13550.130859375, "min": 13550.130859375, "max": 29626.037109375, "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": 54.71003723144531, "min": 0.36059850454330444, "max": 54.71003723144531, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 10668.45703125, "min": 69.95610809326172, "max": 10668.45703125, "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": 0.060940746277029736, "min": 0.059658761472354514, "max": 0.07798176351449608, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24376298510811895, "min": 0.24376298510811895, "max": 0.3783293378068015, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.8765431543191275, "min": 0.15653387025254323, "max": 0.8765431543191275, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 3.50617261727651, "min": 0.6261354810101729, "max": 3.8525834720508723, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.6940973060000025e-06, "min": 2.6940973060000025e-06, "max": 9.729400270599998e-05, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.077638922400001e-05, "min": 1.077638922400001e-05, "max": 0.0004617200382800001, "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": 19.931818181818183, "min": 3.409090909090909, "max": 19.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 877.0, "min": 150.0, "max": 1087.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 19.931818181818183, "min": 3.409090909090909, "max": 19.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 877.0, "min": 150.0, "max": 1087.0, "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": "1684402034", "python_version": "3.9.0 | packaged by conda-forge | (default, Oct 14 2020, 22:59:50) \n[GCC 7.5.0]", "command_line_arguments": "/home/ozsports1/anaconda3/envs/Pytorch/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", "numpy_version": "1.21.2", "end_time_seconds": "1684402252" }, "total": 217.403286063, "count": 1, "self": 0.21841887900018264, "children": { "run_training.setup": { "total": 0.016221298999880673, "count": 1, "self": 0.016221298999880673 }, "TrainerController.start_learning": { "total": 217.16864588499993, "count": 1, "self": 0.37385030795985585, "children": { "TrainerController._reset_env": { "total": 2.7549894670000867, "count": 1, "self": 2.7549894670000867 }, "TrainerController.advance": { "total": 213.9438601930401, "count": 18204, "self": 0.1978863290210029, "children": { "env_step": { "total": 213.7459738640191, "count": 18204, "self": 147.85176191103665, "children": { "SubprocessEnvManager._take_step": { "total": 65.7138327189773, "count": 18204, "self": 1.0025103600169132, "children": { "TorchPolicy.evaluate": { "total": 64.71132235896039, "count": 18204, "self": 64.71132235896039 } } }, "workers": { "total": 0.18037923400515865, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 216.67670963500404, "count": 18204, "is_parallel": true, "self": 119.07478250406848, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010393429997748171, "count": 1, "is_parallel": true, "self": 0.0002793569997265877, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007599860000482295, "count": 10, "is_parallel": true, "self": 0.0007599860000482295 } } }, "UnityEnvironment.step": { "total": 0.015060792999975092, "count": 1, "is_parallel": true, "self": 0.00022294199970929185, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017916300021170173, "count": 1, "is_parallel": true, "self": 0.00017916300021170173 }, "communicator.exchange": { "total": 0.013904264999837324, "count": 1, "is_parallel": true, "self": 0.013904264999837324 }, "steps_from_proto": { "total": 0.0007544230002167751, "count": 1, "is_parallel": true, "self": 0.00017694999996820115, "children": { "_process_rank_one_or_two_observation": { "total": 0.000577473000248574, "count": 10, "is_parallel": true, "self": 0.000577473000248574 } } } } } } }, "UnityEnvironment.step": { "total": 97.60192713093556, "count": 18203, "is_parallel": true, "self": 4.100984776990572, "children": { "UnityEnvironment._generate_step_input": { "total": 2.4853720719902412, "count": 18203, "is_parallel": true, "self": 2.4853720719902412 }, "communicator.exchange": { "total": 77.79749334998223, "count": 18203, "is_parallel": true, "self": 77.79749334998223 }, "steps_from_proto": { "total": 13.218076931972519, "count": 18203, "is_parallel": true, "self": 2.9386955599243265, "children": { "_process_rank_one_or_two_observation": { "total": 10.279381372048192, "count": 182030, "is_parallel": true, "self": 10.279381372048192 } } } } } } } } } } } } }, "trainer_threads": { "total": 8.804599974610028e-05, "count": 1, "self": 8.804599974610028e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 213.6635199020693, "count": 161174, "is_parallel": true, "self": 1.6107290339596148, "children": { "process_trajectory": { "total": 114.6201749231077, "count": 161174, "is_parallel": true, "self": 114.11458840810747, "children": { "RLTrainer._checkpoint": { "total": 0.5055865150002319, "count": 4, "is_parallel": true, "self": 0.5055865150002319 } } }, "_update_policy": { "total": 97.432615945002, "count": 90, "is_parallel": true, "self": 29.361763032010003, "children": { "TorchPPOOptimizer.update": { "total": 68.070852912992, "count": 4587, "is_parallel": true, "self": 68.070852912992 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09585787100013476, "count": 1, "self": 0.0006157800003165903, "children": { "RLTrainer._checkpoint": { "total": 0.09524209099981817, "count": 1, "self": 0.09524209099981817 } } } } } } }