{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7289490103721619, "min": 0.7289490103721619, "max": 2.836063861846924, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6992.0791015625, "min": 6992.0791015625, "max": 28950.5390625, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.117679595947266, "min": 0.4027617573738098, "max": 14.117679595947266, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2894.124267578125, "min": 78.13578033447266, "max": 2894.124267578125, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.13757847411928678, "min": 0.13330649558701735, "max": 0.14574566736471112, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.6878923705964339, "min": 0.5332259823480694, "max": 0.7287283368235555, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.15227453235755947, "min": 0.13715860132931496, "max": 0.2576841875823105, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7613726617877974, "min": 0.5486344053172598, "max": 1.2884209379115525, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.0528989824000028e-06, "min": 3.0528989824000028e-06, "max": 0.00029675280108239997, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5264494912000015e-05, "min": 1.5264494912000015e-05, "max": 0.001454064015312, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10101760000000001, "min": 0.10101760000000001, "max": 0.19891760000000003, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5050880000000001, "min": 0.4119904000000001, "max": 0.9846880000000001, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.077824000000005e-05, "min": 6.077824000000005e-05, "max": 0.00494598824, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00030389120000000027, "min": 0.00030389120000000027, "max": 0.024235931200000005, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.636363636363637, "min": 4.636363636363637, "max": 27.772727272727273, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1520.0, "min": 204.0, "max": 1520.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.636363636363637, "min": 4.636363636363637, "max": 27.772727272727273, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1520.0, "min": 204.0, "max": 1520.0, "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": "1739417797", "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=SnowballTarget1 --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": "1739420326" }, "total": 2528.317316521, "count": 1, "self": 0.54252609499963, "children": { "run_training.setup": { "total": 0.02956287400002111, "count": 1, "self": 0.02956287400002111 }, "TrainerController.start_learning": { "total": 2527.7452275520004, "count": 1, "self": 1.538237926851707, "children": { "TrainerController._reset_env": { "total": 4.0532582740002, "count": 1, "self": 4.0532582740002 }, "TrainerController.advance": { "total": 2522.0642549951476, "count": 45464, "self": 1.752069157951155, "children": { "env_step": { "total": 987.4326356369684, "count": 45464, "self": 832.7121209879065, "children": { "SubprocessEnvManager._take_step": { "total": 153.76910981404262, "count": 45464, "self": 5.243402144053107, "children": { "TorchPolicy.evaluate": { "total": 148.52570766998952, "count": 45464, "self": 148.52570766998952 } } }, "workers": { "total": 0.9514048350192752, "count": 45464, "self": 0.0, "children": { "worker_root": { "total": 2522.871541284004, "count": 45464, "is_parallel": true, "self": 1804.7961187858396, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004584772999805864, "count": 1, "is_parallel": true, "self": 0.001470133999191603, "children": { "_process_rank_one_or_two_observation": { "total": 0.003114639000614261, "count": 10, "is_parallel": true, "self": 0.003114639000614261 } } }, "UnityEnvironment.step": { "total": 0.045112181000149576, "count": 1, "is_parallel": true, "self": 0.0006979620002312004, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004509790001065994, "count": 1, "is_parallel": true, "self": 0.0004509790001065994 }, "communicator.exchange": { "total": 0.041757342999972025, "count": 1, "is_parallel": true, "self": 0.041757342999972025 }, "steps_from_proto": { "total": 0.0022058969998397515, "count": 1, "is_parallel": true, "self": 0.00047695000012026867, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017289469997194828, "count": 10, "is_parallel": true, "self": 0.0017289469997194828 } } } } } } }, "UnityEnvironment.step": { "total": 718.0754224981642, "count": 45463, "is_parallel": true, "self": 33.36629272099117, "children": { "UnityEnvironment._generate_step_input": { "total": 18.351658924047115, "count": 45463, "is_parallel": true, "self": 18.351658924047115 }, "communicator.exchange": { "total": 564.2250598290857, "count": 45463, "is_parallel": true, "self": 564.2250598290857 }, "steps_from_proto": { "total": 102.13241102404027, "count": 45463, "is_parallel": true, "self": 19.690268941010345, "children": { "_process_rank_one_or_two_observation": { "total": 82.44214208302992, "count": 454630, "is_parallel": true, "self": 82.44214208302992 } } } } } } } } } } }, "trainer_advance": { "total": 1532.879550200228, "count": 45464, "self": 2.0429937933163274, "children": { "process_trajectory": { "total": 79.40037021691433, "count": 45464, "self": 78.1602372649163, "children": { "RLTrainer._checkpoint": { "total": 1.2401329519980209, "count": 10, "self": 1.2401329519980209 } } }, "_update_policy": { "total": 1451.4361861899974, "count": 227, "self": 226.6616541349058, "children": { "TorchPPOOptimizer.update": { "total": 1224.7745320550916, "count": 77170, "self": 1224.7745320550916 } } } } } } }, "trainer_threads": { "total": 1.2240006981301121e-06, "count": 1, "self": 1.2240006981301121e-06 }, "TrainerController._save_models": { "total": 0.08947513200018875, "count": 1, "self": 0.0014119140005277586, "children": { "RLTrainer._checkpoint": { "total": 0.08806321799966099, "count": 1, "self": 0.08806321799966099 } } } } } } }