{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9928900003433228, "min": 0.9928900003433228, "max": 2.8700194358825684, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9512.87890625, "min": 9512.87890625, "max": 29455.009765625, "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": 12.96102237701416, "min": 0.41540929675102234, "max": 12.96102237701416, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2527.3994140625, "min": 80.58940124511719, "max": 2603.254150390625, "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": 0.0692171166852395, "min": 0.06248207283251937, "max": 0.0732661069295336, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.276868466740958, "min": 0.2499282913300775, "max": 0.36630038717332497, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1983239668257096, "min": 0.1328368166132885, "max": 0.28478162539940255, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7932958673028384, "min": 0.531347266453154, "max": 1.4239081269970129, "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": 25.068181818181817, "min": 3.5, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1103.0, "min": 154.0, "max": 1397.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.068181818181817, "min": 3.5, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1103.0, "min": 154.0, "max": 1397.0, "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": "1700314248", "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": "1700314836" }, "total": 587.752699368, "count": 1, "self": 0.4889640869999994, "children": { "run_training.setup": { "total": 0.05537232799997582, "count": 1, "self": 0.05537232799997582 }, "TrainerController.start_learning": { "total": 587.208362953, "count": 1, "self": 0.8342887989929295, "children": { "TrainerController._reset_env": { "total": 2.6802054179999004, "count": 1, "self": 2.6802054179999004 }, "TrainerController.advance": { "total": 583.5903262230071, "count": 18203, "self": 0.398088206999887, "children": { "env_step": { "total": 583.1922380160072, "count": 18203, "self": 458.65353490099085, "children": { "SubprocessEnvManager._take_step": { "total": 124.14232303201288, "count": 18203, "self": 2.1568949480224546, "children": { "TorchPolicy.evaluate": { "total": 121.98542808399043, "count": 18203, "self": 121.98542808399043 } } }, "workers": { "total": 0.3963800830034643, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 585.1962042509829, "count": 18203, "is_parallel": true, "self": 266.8320587239888, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0060473400000091715, "count": 1, "is_parallel": true, "self": 0.003962778999834882, "children": { "_process_rank_one_or_two_observation": { "total": 0.00208456100017429, "count": 10, "is_parallel": true, "self": 0.00208456100017429 } } }, "UnityEnvironment.step": { "total": 0.08749124199994185, "count": 1, "is_parallel": true, "self": 0.0007503329998144181, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004268870000032621, "count": 1, "is_parallel": true, "self": 0.0004268870000032621 }, "communicator.exchange": { "total": 0.08419595400005164, "count": 1, "is_parallel": true, "self": 0.08419595400005164 }, "steps_from_proto": { "total": 0.002118068000072526, "count": 1, "is_parallel": true, "self": 0.00039913700027227605, "children": { "_process_rank_one_or_two_observation": { "total": 0.00171893099980025, "count": 10, "is_parallel": true, "self": 0.00171893099980025 } } } } } } }, "UnityEnvironment.step": { "total": 318.3641455269941, "count": 18202, "is_parallel": true, "self": 13.98556429901521, "children": { "UnityEnvironment._generate_step_input": { "total": 7.588917484995704, "count": 18202, "is_parallel": true, "self": 7.588917484995704 }, "communicator.exchange": { "total": 252.5310534139919, "count": 18202, "is_parallel": true, "self": 252.5310534139919 }, "steps_from_proto": { "total": 44.25861032899127, "count": 18202, "is_parallel": true, "self": 8.709703911984775, "children": { "_process_rank_one_or_two_observation": { "total": 35.54890641700649, "count": 182020, "is_parallel": true, "self": 35.54890641700649 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002320240000699414, "count": 1, "self": 0.0002320240000699414, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 578.6864097090277, "count": 591666, "is_parallel": true, "self": 13.07654631300511, "children": { "process_trajectory": { "total": 315.93861322502255, "count": 591666, "is_parallel": true, "self": 315.06688950602245, "children": { "RLTrainer._checkpoint": { "total": 0.8717237190001015, "count": 4, "is_parallel": true, "self": 0.8717237190001015 } } }, "_update_policy": { "total": 249.671250171, "count": 90, "is_parallel": true, "self": 75.25077742399674, "children": { "TorchPPOOptimizer.update": { "total": 174.42047274700326, "count": 4584, "is_parallel": true, "self": 174.42047274700326 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10331048900002315, "count": 1, "self": 0.0010682020001695491, "children": { "RLTrainer._checkpoint": { "total": 0.1022422869998536, "count": 1, "self": 0.1022422869998536 } } } } } } }