{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9996548295021057, "min": 0.9996548295021057, "max": 2.8652329444885254, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9533.7080078125, "min": 9533.7080078125, "max": 29563.474609375, "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": 12.577868461608887, "min": 0.2449164241552353, "max": 12.577868461608887, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2452.684326171875, "min": 47.51378631591797, "max": 2538.02490234375, "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": 0.06902327295991947, "min": 0.06105987916257707, "max": 0.07649442223003408, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2760930918396779, "min": 0.24724468106504383, "max": 0.38247211115017044, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1908779824335201, "min": 0.1129165241579233, "max": 0.26910442362229026, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7635119297340804, "min": 0.4516660966316932, "max": 1.3455221181114514, "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": 24.90909090909091, "min": 3.340909090909091, "max": 24.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1096.0, "min": 147.0, "max": 1360.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.90909090909091, "min": 3.340909090909091, "max": 24.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1096.0, "min": 147.0, "max": 1360.0, "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": "1714048563", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714049005" }, "total": 441.923823158, "count": 1, "self": 0.4356822500000703, "children": { "run_training.setup": { "total": 0.056996612999967056, "count": 1, "self": 0.056996612999967056 }, "TrainerController.start_learning": { "total": 441.43114429499997, "count": 1, "self": 0.5539116439862255, "children": { "TrainerController._reset_env": { "total": 3.469510523999986, "count": 1, "self": 3.469510523999986 }, "TrainerController.advance": { "total": 437.30698943101373, "count": 18198, "self": 0.2543840290035746, "children": { "env_step": { "total": 437.05260540201016, "count": 18198, "self": 283.7404958240149, "children": { "SubprocessEnvManager._take_step": { "total": 153.0429903149947, "count": 18198, "self": 1.4288170169937189, "children": { "TorchPolicy.evaluate": { "total": 151.614173298001, "count": 18198, "self": 151.614173298001 } } }, "workers": { "total": 0.26911926300056166, "count": 18198, "self": 0.0, "children": { "worker_root": { "total": 440.32153010799425, "count": 18198, "is_parallel": true, "self": 220.22458482299885, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0059637019999740914, "count": 1, "is_parallel": true, "self": 0.004210490000048139, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017532119999259521, "count": 10, "is_parallel": true, "self": 0.0017532119999259521 } } }, "UnityEnvironment.step": { "total": 0.03624722900002553, "count": 1, "is_parallel": true, "self": 0.0006478320000269377, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039075400002275273, "count": 1, "is_parallel": true, "self": 0.00039075400002275273 }, "communicator.exchange": { "total": 0.03303908599997385, "count": 1, "is_parallel": true, "self": 0.03303908599997385 }, "steps_from_proto": { "total": 0.002169557000001987, "count": 1, "is_parallel": true, "self": 0.00041102899996303677, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017585280000389503, "count": 10, "is_parallel": true, "self": 0.0017585280000389503 } } } } } } }, "UnityEnvironment.step": { "total": 220.0969452849954, "count": 18197, "is_parallel": true, "self": 10.160521058996778, "children": { "UnityEnvironment._generate_step_input": { "total": 5.217351725000867, "count": 18197, "is_parallel": true, "self": 5.217351725000867 }, "communicator.exchange": { "total": 171.72802630400014, "count": 18197, "is_parallel": true, "self": 171.72802630400014 }, "steps_from_proto": { "total": 32.991046196997615, "count": 18197, "is_parallel": true, "self": 6.0567448169953195, "children": { "_process_rank_one_or_two_observation": { "total": 26.934301380002296, "count": 181970, "is_parallel": true, "self": 26.934301380002296 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.000143839999964257, "count": 1, "self": 0.000143839999964257, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 432.10136792302717, "count": 649918, "is_parallel": true, "self": 13.47861723899507, "children": { "process_trajectory": { "total": 238.35443177603213, "count": 649918, "is_parallel": true, "self": 237.5594449830321, "children": { "RLTrainer._checkpoint": { "total": 0.794986793000021, "count": 4, "is_parallel": true, "self": 0.794986793000021 } } }, "_update_policy": { "total": 180.26831890799997, "count": 90, "is_parallel": true, "self": 50.89474907799405, "children": { "TorchPPOOptimizer.update": { "total": 129.37356983000592, "count": 4584, "is_parallel": true, "self": 129.37356983000592 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10058885600005851, "count": 1, "self": 0.001183675000106632, "children": { "RLTrainer._checkpoint": { "total": 0.09940518099995188, "count": 1, "self": 0.09940518099995188 } } } } } } }