{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.006709337234497, "min": 1.006709337234497, "max": 2.864173173904419, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9612.060546875, "min": 9612.060546875, "max": 29395.009765625, "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": 11.996334075927734, "min": 0.3177822232246399, "max": 12.014837265014648, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2339.28515625, "min": 61.64975357055664, "max": 2451.02685546875, "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": 0.06984036025824025, "min": 0.06108423119248805, "max": 0.07615923770394076, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.279361441032961, "min": 0.2545921234864805, "max": 0.36159105115503365, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20112433028863927, "min": 0.10848450459660872, "max": 0.28268590554887174, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8044973211545571, "min": 0.43393801838643487, "max": 1.3106496345763115, "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": 23.818181818181817, "min": 3.25, "max": 23.818181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1048.0, "min": 143.0, "max": 1294.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.818181818181817, "min": 3.25, "max": 23.818181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1048.0, "min": 143.0, "max": 1294.0, "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": "1701100453", "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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701100952" }, "total": 499.5031696479998, "count": 1, "self": 0.7822285069996724, "children": { "run_training.setup": { "total": 0.060827821999964726, "count": 1, "self": 0.060827821999964726 }, "TrainerController.start_learning": { "total": 498.6601133190002, "count": 1, "self": 0.6405420679907365, "children": { "TrainerController._reset_env": { "total": 4.440519054999868, "count": 1, "self": 4.440519054999868 }, "TrainerController.advance": { "total": 493.4364566880097, "count": 18199, "self": 0.32158226798560463, "children": { "env_step": { "total": 493.1148744200241, "count": 18199, "self": 337.9749713290694, "children": { "SubprocessEnvManager._take_step": { "total": 154.81815013598884, "count": 18199, "self": 1.556145688006609, "children": { "TorchPolicy.evaluate": { "total": 153.26200444798224, "count": 18199, "self": 153.26200444798224 } } }, "workers": { "total": 0.3217529549658593, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 497.2482991600061, "count": 18199, "is_parallel": true, "self": 243.81574547099103, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00596211700008098, "count": 1, "is_parallel": true, "self": 0.0038308880000386125, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021312290000423673, "count": 10, "is_parallel": true, "self": 0.0021312290000423673 } } }, "UnityEnvironment.step": { "total": 0.03775803200005612, "count": 1, "is_parallel": true, "self": 0.0034955150001678703, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004095140000117681, "count": 1, "is_parallel": true, "self": 0.0004095140000117681 }, "communicator.exchange": { "total": 0.03184841500001312, "count": 1, "is_parallel": true, "self": 0.03184841500001312 }, "steps_from_proto": { "total": 0.002004587999863361, "count": 1, "is_parallel": true, "self": 0.00040410599990536866, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016004819999579922, "count": 10, "is_parallel": true, "self": 0.0016004819999579922 } } } } } } }, "UnityEnvironment.step": { "total": 253.4325536890151, "count": 18198, "is_parallel": true, "self": 10.633412111014877, "children": { "UnityEnvironment._generate_step_input": { "total": 5.474986393018526, "count": 18198, "is_parallel": true, "self": 5.474986393018526 }, "communicator.exchange": { "total": 203.12878586297415, "count": 18198, "is_parallel": true, "self": 203.12878586297415 }, "steps_from_proto": { "total": 34.19536932200754, "count": 18198, "is_parallel": true, "self": 6.537842645088858, "children": { "_process_rank_one_or_two_observation": { "total": 27.65752667691868, "count": 181980, "is_parallel": true, "self": 27.65752667691868 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001274889996238926, "count": 1, "self": 0.0001274889996238926, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 489.12730825092103, "count": 528934, "is_parallel": true, "self": 11.284875172738566, "children": { "process_trajectory": { "total": 276.04658962818166, "count": 528934, "is_parallel": true, "self": 275.2287628381821, "children": { "RLTrainer._checkpoint": { "total": 0.8178267899995717, "count": 4, "is_parallel": true, "self": 0.8178267899995717 } } }, "_update_policy": { "total": 201.7958434500008, "count": 90, "is_parallel": true, "self": 68.51273517798927, "children": { "TorchPPOOptimizer.update": { "total": 133.28310827201153, "count": 4587, "is_parallel": true, "self": 133.28310827201153 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14246801900026185, "count": 1, "self": 0.0012432310004442115, "children": { "RLTrainer._checkpoint": { "total": 0.14122478799981764, "count": 1, "self": 0.14122478799981764 } } } } } } }