{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9758440852165222, "min": 0.9486198425292969, "max": 2.851512908935547, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9317.359375, "min": 9317.359375, "max": 29327.810546875, "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": 11.753535270690918, "min": 0.5047515630722046, "max": 11.753535270690918, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2291.939453125, "min": 97.92180633544922, "max": 2368.2734375, "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": 0.06503404497840058, "min": 0.06054439537739895, "max": 0.0770660569590594, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26013617991360233, "min": 0.2421775815095958, "max": 0.358154390208131, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1907297268363775, "min": 0.1277231928052417, "max": 0.26889650143829047, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.76291890734551, "min": 0.5108927712209668, "max": 1.2944090322536579, "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": 23.5, "min": 3.6818181818181817, "max": 23.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1034.0, "min": 162.0, "max": 1267.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.5, "min": 3.6818181818181817, "max": 23.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1034.0, "min": 162.0, "max": 1267.0, "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": "1700725599", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700726051" }, "total": 452.03190814800007, "count": 1, "self": 0.42792070300009755, "children": { "run_training.setup": { "total": 0.04436259300001666, "count": 1, "self": 0.04436259300001666 }, "TrainerController.start_learning": { "total": 451.55962485199996, "count": 1, "self": 0.4939525169975809, "children": { "TrainerController._reset_env": { "total": 9.428729562000001, "count": 1, "self": 9.428729562000001 }, "TrainerController.advance": { "total": 441.55443397600243, "count": 18199, "self": 0.2403902180027444, "children": { "env_step": { "total": 441.3140437579997, "count": 18199, "self": 301.70787899399534, "children": { "SubprocessEnvManager._take_step": { "total": 139.3478270669994, "count": 18199, "self": 1.3487460479927336, "children": { "TorchPolicy.evaluate": { "total": 137.99908101900667, "count": 18199, "self": 137.99908101900667 } } }, "workers": { "total": 0.25833769700494713, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 450.34856881901044, "count": 18199, "is_parallel": true, "self": 223.12855201400112, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0051648699999873315, "count": 1, "is_parallel": true, "self": 0.0034619869999801267, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017028830000072048, "count": 10, "is_parallel": true, "self": 0.0017028830000072048 } } }, "UnityEnvironment.step": { "total": 0.04249261400002524, "count": 1, "is_parallel": true, "self": 0.0006133740000109356, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003842819999704261, "count": 1, "is_parallel": true, "self": 0.0003842819999704261 }, "communicator.exchange": { "total": 0.039553780000005645, "count": 1, "is_parallel": true, "self": 0.039553780000005645 }, "steps_from_proto": { "total": 0.001941178000038235, "count": 1, "is_parallel": true, "self": 0.00039557200005901905, "children": { "_process_rank_one_or_two_observation": { "total": 0.001545605999979216, "count": 10, "is_parallel": true, "self": 0.001545605999979216 } } } } } } }, "UnityEnvironment.step": { "total": 227.22001680500932, "count": 18198, "is_parallel": true, "self": 10.142361390025428, "children": { "UnityEnvironment._generate_step_input": { "total": 5.14840288399796, "count": 18198, "is_parallel": true, "self": 5.14840288399796 }, "communicator.exchange": { "total": 180.2717971889897, "count": 18198, "is_parallel": true, "self": 180.2717971889897 }, "steps_from_proto": { "total": 31.65745534199624, "count": 18198, "is_parallel": true, "self": 5.696431092987154, "children": { "_process_rank_one_or_two_observation": { "total": 25.961024249009085, "count": 181980, "is_parallel": true, "self": 25.961024249009085 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011484499998459796, "count": 1, "self": 0.00011484499998459796, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 438.0056552219773, "count": 460738, "is_parallel": true, "self": 9.727342678018374, "children": { "process_trajectory": { "total": 246.3335763309592, "count": 460738, "is_parallel": true, "self": 245.7136922589592, "children": { "RLTrainer._checkpoint": { "total": 0.6198840719999907, "count": 4, "is_parallel": true, "self": 0.6198840719999907 } } }, "_update_policy": { "total": 181.94473621299971, "count": 90, "is_parallel": true, "self": 58.53403750399974, "children": { "TorchPPOOptimizer.update": { "total": 123.41069870899997, "count": 4587, "is_parallel": true, "self": 123.41069870899997 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08239395199996125, "count": 1, "self": 0.0008132269998668562, "children": { "RLTrainer._checkpoint": { "total": 0.08158072500009439, "count": 1, "self": 0.08158072500009439 } } } } } } }