{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9324012398719788, "min": 0.9324012398719788, "max": 2.8693699836730957, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8984.6181640625, "min": 8984.6181640625, "max": 29606.16015625, "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": 12.775907516479492, "min": 0.21746708452701569, "max": 12.775907516479492, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2491.302001953125, "min": 42.18861389160156, "max": 2599.271240234375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07074688270764526, "min": 0.05807069648775117, "max": 0.07531241589298873, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28298753083058104, "min": 0.23228278595100468, "max": 0.3765620794649437, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19052539349478834, "min": 0.10797299232160418, "max": 0.29982486075046016, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7621015739791533, "min": 0.4318919692864167, "max": 1.45575645273807, "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": 25.0, "min": 3.272727272727273, "max": 25.10909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1100.0, "min": 144.0, "max": 1381.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.0, "min": 3.272727272727273, "max": 25.10909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1100.0, "min": 144.0, "max": 1381.0, "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": "1680623070", "python_version": "3.10.10 | packaged by conda-forge | (main, Mar 24 2023, 20:08:06) [GCC 11.3.0]", "command_line_arguments": "/home/kian/anaconda3/envs/torch-2/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.0", "numpy_version": "1.21.2", "end_time_seconds": "1680624726" }, "total": 1656.6096646280002, "count": 1, "self": 0.34299334200022713, "children": { "run_training.setup": { "total": 0.013044695000189677, "count": 1, "self": 0.013044695000189677 }, "TrainerController.start_learning": { "total": 1656.2536265909998, "count": 1, "self": 0.5980244529937409, "children": { "TrainerController._reset_env": { "total": 3.6993506949997936, "count": 1, "self": 3.6993506949997936 }, "TrainerController.advance": { "total": 1651.7884615040066, "count": 18208, "self": 0.17021598799328785, "children": { "env_step": { "total": 1651.6182455160133, "count": 18208, "self": 326.91946066509763, "children": { "SubprocessEnvManager._take_step": { "total": 1324.5161174039658, "count": 18208, "self": 1.2219899609949607, "children": { "TorchPolicy.evaluate": { "total": 1323.2941274429709, "count": 18208, "self": 1323.2941274429709 } } }, "workers": { "total": 0.18266744694983572, "count": 18208, "self": 0.0, "children": { "worker_root": { "total": 1655.517983508042, "count": 18208, "is_parallel": true, "self": 1542.2279728410285, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012097959997845464, "count": 1, "is_parallel": true, "self": 0.000343598999279493, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008661970005050534, "count": 10, "is_parallel": true, "self": 0.0008661970005050534 } } }, "UnityEnvironment.step": { "total": 0.015171707999797945, "count": 1, "is_parallel": true, "self": 0.00023231800014400505, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020259000029909657, "count": 1, "is_parallel": true, "self": 0.00020259000029909657 }, "communicator.exchange": { "total": 0.01395424299971637, "count": 1, "is_parallel": true, "self": 0.01395424299971637 }, "steps_from_proto": { "total": 0.0007825569996384729, "count": 1, "is_parallel": true, "self": 0.00017048900053850957, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006120679990999633, "count": 10, "is_parallel": true, "self": 0.0006120679990999633 } } } } } } }, "UnityEnvironment.step": { "total": 113.29001066701358, "count": 18207, "is_parallel": true, "self": 4.3960231939640835, "children": { "UnityEnvironment._generate_step_input": { "total": 2.9347652479705175, "count": 18207, "is_parallel": true, "self": 2.9347652479705175 }, "communicator.exchange": { "total": 91.26440036107897, "count": 18207, "is_parallel": true, "self": 91.26440036107897 }, "steps_from_proto": { "total": 14.694821864000005, "count": 18207, "is_parallel": true, "self": 2.8643088949065714, "children": { "_process_rank_one_or_two_observation": { "total": 11.830512969093434, "count": 182070, "is_parallel": true, "self": 11.830512969093434 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018820999957824824, "count": 1, "self": 0.00018820999957824824, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1645.5939395193154, "count": 3109797, "is_parallel": true, "self": 15.485322908098624, "children": { "process_trajectory": { "total": 985.8543664352142, "count": 3109797, "is_parallel": true, "self": 984.8976165382137, "children": { "RLTrainer._checkpoint": { "total": 0.9567498970004635, "count": 4, "is_parallel": true, "self": 0.9567498970004635 } } }, "_update_policy": { "total": 644.2542501760026, "count": 90, "is_parallel": true, "self": 26.743431131987563, "children": { "TorchPPOOptimizer.update": { "total": 617.5108190440151, "count": 4587, "is_parallel": true, "self": 617.5108190440151 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1676017290001255, "count": 1, "self": 0.0009011470001496491, "children": { "RLTrainer._checkpoint": { "total": 0.16670058199997584, "count": 1, "self": 0.16670058199997584 } } } } } } }