{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1345734596252441, "min": 1.1345734596252441, "max": 2.8691322803497314, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11581.7255859375, "min": 10572.2158203125, "max": 30406.484375, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499912.0, "min": 9952.0, "max": 499912.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499912.0, "min": 9952.0, "max": 499912.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.168490409851074, "min": 0.0590021125972271, "max": 14.174521446228027, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1431.017578125, "min": 5.723205089569092, "max": 1457.92919921875, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.62264150943396, "min": 2.8636363636363638, "max": 28.074074074074073, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1464.0, "min": 126.0, "max": 1537.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.62264150943396, "min": 2.8636363636363638, "max": 28.074074074074073, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1464.0, "min": 126.0, "max": 1537.0, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.052467593056944144, "min": 0.04180766746032853, "max": 0.05869223219997366, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.10493518611388829, "min": 0.08361533492065706, "max": 0.16203350899334457, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.13142435532063246, "min": 0.11110193868551184, "max": 0.3132188031997751, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.2628487106412649, "min": 0.22220387737102368, "max": 0.9317585683482534, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.0000990000000026e-06, "min": 3.0000990000000026e-06, "max": 0.00029604000132, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 6.000198000000005e-06, "min": 6.000198000000005e-06, "max": 0.0008366400211199997, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10099999999999999, "min": 0.10099999999999999, "max": 0.19868000000000002, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.20199999999999999, "min": 0.20199999999999999, "max": 0.5788800000000001, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00010990000000000008, "min": 0.00010990000000000008, "max": 0.009868132, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00021980000000000017, "min": 0.00021980000000000017, "max": 0.027890112, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1742156409", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742157794" }, "total": 1385.2139096370001, "count": 1, "self": 0.5271425620003356, "children": { "run_training.setup": { "total": 0.023999615999969137, "count": 1, "self": 0.023999615999969137 }, "TrainerController.start_learning": { "total": 1384.662767459, "count": 1, "self": 1.300557343005039, "children": { "TrainerController._reset_env": { "total": 2.33786494200001, "count": 1, "self": 2.33786494200001 }, "TrainerController.advance": { "total": 1380.655655529995, "count": 45528, "self": 1.2949069360033718, "children": { "env_step": { "total": 972.278138391983, "count": 45528, "self": 716.4956075479805, "children": { "SubprocessEnvManager._take_step": { "total": 254.99298378899925, "count": 45528, "self": 4.121920378987511, "children": { "TorchPolicy.evaluate": { "total": 250.87106341001174, "count": 45528, "self": 250.87106341001174 } } }, "workers": { "total": 0.7895470550032542, "count": 45528, "self": 0.0, "children": { "worker_root": { "total": 1379.9994235519907, "count": 45528, "is_parallel": true, "self": 755.066043718004, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002461629000094945, "count": 1, "is_parallel": true, "self": 0.0007591230001935401, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017025059999014047, "count": 10, "is_parallel": true, "self": 0.0017025059999014047 } } }, "UnityEnvironment.step": { "total": 0.03980099099999279, "count": 1, "is_parallel": true, "self": 0.0006900690000293253, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043215999994572485, "count": 1, "is_parallel": true, "self": 0.00043215999994572485 }, "communicator.exchange": { "total": 0.03660692400001153, "count": 1, "is_parallel": true, "self": 0.03660692400001153 }, "steps_from_proto": { "total": 0.0020718380000062098, "count": 1, "is_parallel": true, "self": 0.0003966610001953086, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016751769998109012, "count": 10, "is_parallel": true, "self": 0.0016751769998109012 } } } } } } }, "UnityEnvironment.step": { "total": 624.9333798339867, "count": 45527, "is_parallel": true, "self": 29.70215981395461, "children": { "UnityEnvironment._generate_step_input": { "total": 16.148238608045517, "count": 45527, "is_parallel": true, "self": 16.148238608045517 }, "communicator.exchange": { "total": 486.3774410230102, "count": 45527, "is_parallel": true, "self": 486.3774410230102 }, "steps_from_proto": { "total": 92.70554038897637, "count": 45527, "is_parallel": true, "self": 17.410760163032137, "children": { "_process_rank_one_or_two_observation": { "total": 75.29478022594424, "count": 455270, "is_parallel": true, "self": 75.29478022594424 } } } } } } } } } } }, "trainer_advance": { "total": 407.0826102020087, "count": 45528, "self": 1.6338905880062384, "children": { "process_trajectory": { "total": 101.1737255460024, "count": 45528, "self": 98.8063373920022, "children": { "RLTrainer._checkpoint": { "total": 2.3673881540001958, "count": 10, "self": 2.3673881540001958 } } }, "_update_policy": { "total": 304.27499406800007, "count": 113, "self": 157.9587098709884, "children": { "TorchPPOOptimizer.update": { "total": 146.31628419701167, "count": 7684, "self": 146.31628419701167 } } } } } } }, "trainer_threads": { "total": 1.0499998097657226e-06, "count": 1, "self": 1.0499998097657226e-06 }, "TrainerController._save_models": { "total": 0.3686885940001048, "count": 1, "self": 0.003009602000020095, "children": { "RLTrainer._checkpoint": { "total": 0.3656789920000847, "count": 1, "self": 0.3656789920000847 } } } } } } }