{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1256626844406128, "min": 1.1256626844406128, "max": 2.8609366416931152, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10735.4453125, "min": 10735.4453125, "max": 29361.79296875, "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": 11.738016128540039, "min": 0.5861009359359741, "max": 11.738016128540039, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2288.9130859375, "min": 113.70358276367188, "max": 2352.447509765625, "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": 0.06664960866014465, "min": 0.06136969322802079, "max": 0.07309905315488839, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2665984346405786, "min": 0.24547877291208317, "max": 0.3608087172874993, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18445931152239733, "min": 0.15272608458968426, "max": 0.27350295098388894, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7378372460895893, "min": 0.610904338358737, "max": 1.3675147549194446, "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": 23.636363636363637, "min": 4.159090909090909, "max": 23.636363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1040.0, "min": 183.0, "max": 1277.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.636363636363637, "min": 4.159090909090909, "max": 23.636363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1040.0, "min": 183.0, "max": 1277.0, "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": "1700725942", "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": "1700726458" }, "total": 516.403559946, "count": 1, "self": 0.4258133140000382, "children": { "run_training.setup": { "total": 0.050145450000002256, "count": 1, "self": 0.050145450000002256 }, "TrainerController.start_learning": { "total": 515.927601182, "count": 1, "self": 0.5901721500058557, "children": { "TrainerController._reset_env": { "total": 11.068037057999959, "count": 1, "self": 11.068037057999959 }, "TrainerController.advance": { "total": 504.1711175729942, "count": 18199, "self": 0.2825441489978857, "children": { "env_step": { "total": 503.8885734239963, "count": 18199, "self": 347.55728937699337, "children": { "SubprocessEnvManager._take_step": { "total": 155.89251201700768, "count": 18199, "self": 1.5406164860104354, "children": { "TorchPolicy.evaluate": { "total": 154.35189553099724, "count": 18199, "self": 154.35189553099724 } } }, "workers": { "total": 0.43877202999527753, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 514.4553518639977, "count": 18199, "is_parallel": true, "self": 254.00517901500177, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006218901000011101, "count": 1, "is_parallel": true, "self": 0.004604712000002564, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016141890000085368, "count": 10, "is_parallel": true, "self": 0.0016141890000085368 } } }, "UnityEnvironment.step": { "total": 0.05065842999999859, "count": 1, "is_parallel": true, "self": 0.0007022200000506018, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004167799999663657, "count": 1, "is_parallel": true, "self": 0.0004167799999663657 }, "communicator.exchange": { "total": 0.047151954000014484, "count": 1, "is_parallel": true, "self": 0.047151954000014484 }, "steps_from_proto": { "total": 0.002387475999967137, "count": 1, "is_parallel": true, "self": 0.0005709429999001259, "children": { "_process_rank_one_or_two_observation": { "total": 0.001816533000067011, "count": 10, "is_parallel": true, "self": 0.001816533000067011 } } } } } } }, "UnityEnvironment.step": { "total": 260.450172848996, "count": 18198, "is_parallel": true, "self": 11.66819776098987, "children": { "UnityEnvironment._generate_step_input": { "total": 5.757660393004812, "count": 18198, "is_parallel": true, "self": 5.757660393004812 }, "communicator.exchange": { "total": 205.90590315700217, "count": 18198, "is_parallel": true, "self": 205.90590315700217 }, "steps_from_proto": { "total": 37.11841153799912, "count": 18198, "is_parallel": true, "self": 7.149924786015902, "children": { "_process_rank_one_or_two_observation": { "total": 29.96848675198322, "count": 181980, "is_parallel": true, "self": 29.96848675198322 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012808500002847722, "count": 1, "self": 0.00012808500002847722, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 499.68063952697827, "count": 519048, "is_parallel": true, "self": 11.550333757943577, "children": { "process_trajectory": { "total": 279.55057404903476, "count": 519048, "is_parallel": true, "self": 278.9821034930349, "children": { "RLTrainer._checkpoint": { "total": 0.568470555999852, "count": 4, "is_parallel": true, "self": 0.568470555999852 } } }, "_update_policy": { "total": 208.57973171999993, "count": 90, "is_parallel": true, "self": 71.87472291299883, "children": { "TorchPPOOptimizer.update": { "total": 136.7050088070011, "count": 4587, "is_parallel": true, "self": 136.7050088070011 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09814631599999757, "count": 1, "self": 0.0009594590000006065, "children": { "RLTrainer._checkpoint": { "total": 0.09718685699999696, "count": 1, "self": 0.09718685699999696 } } } } } } }