{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9127944111824036, "min": 0.9074423909187317, "max": 2.8542144298553467, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8675.1982421875, "min": 8675.1982421875, "max": 29135.8203125, "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": 12.534477233886719, "min": 0.41757717728614807, "max": 12.534477233886719, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2444.22314453125, "min": 81.00997161865234, "max": 2541.881103515625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0748984204219596, "min": 0.06026584630179807, "max": 0.0748984204219596, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2995936816878384, "min": 0.24106338520719228, "max": 0.35726796503335134, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24224751011705864, "min": 0.12895162650452488, "max": 0.3136921890956514, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9689900404682346, "min": 0.5158065060180995, "max": 1.4442788470609518, "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.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.Environment.CumulativeReward.mean": { "value": 24.704545454545453, "min": 3.159090909090909, "max": 25.15909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1087.0, "min": 139.0, "max": 1369.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.704545454545453, "min": 3.159090909090909, "max": 25.15909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1087.0, "min": 139.0, "max": 1369.0, "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": "1741173271", "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 --force", "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": "1741173708" }, "total": 437.5261346949999, "count": 1, "self": 0.42487977699965995, "children": { "run_training.setup": { "total": 0.020628942000030293, "count": 1, "self": 0.020628942000030293 }, "TrainerController.start_learning": { "total": 437.0806259760002, "count": 1, "self": 0.37608510600466616, "children": { "TrainerController._reset_env": { "total": 3.111095017000025, "count": 1, "self": 3.111095017000025 }, "TrainerController.advance": { "total": 433.50349633599535, "count": 18192, "self": 0.41063915798577, "children": { "env_step": { "total": 308.83656121098943, "count": 18192, "self": 234.392979108997, "children": { "SubprocessEnvManager._take_step": { "total": 74.22531829400577, "count": 18192, "self": 1.314486041021837, "children": { "TorchPolicy.evaluate": { "total": 72.91083225298394, "count": 18192, "self": 72.91083225298394 } } }, "workers": { "total": 0.21826380798665923, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 435.5094698380001, "count": 18192, "is_parallel": true, "self": 230.4371294670002, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.010315555000033783, "count": 1, "is_parallel": true, "self": 0.008767512000304123, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015480429997296596, "count": 10, "is_parallel": true, "self": 0.0015480429997296596 } } }, "UnityEnvironment.step": { "total": 0.05430213600016032, "count": 1, "is_parallel": true, "self": 0.0005893809998269717, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00035281200007375446, "count": 1, "is_parallel": true, "self": 0.00035281200007375446 }, "communicator.exchange": { "total": 0.05156121700019867, "count": 1, "is_parallel": true, "self": 0.05156121700019867 }, "steps_from_proto": { "total": 0.001798726000060924, "count": 1, "is_parallel": true, "self": 0.0003567759999896225, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014419500000713015, "count": 10, "is_parallel": true, "self": 0.0014419500000713015 } } } } } } }, "UnityEnvironment.step": { "total": 205.07234037099988, "count": 18191, "is_parallel": true, "self": 9.684191109995936, "children": { "UnityEnvironment._generate_step_input": { "total": 5.5035217980087054, "count": 18191, "is_parallel": true, "self": 5.5035217980087054 }, "communicator.exchange": { "total": 157.42518294600268, "count": 18191, "is_parallel": true, "self": 157.42518294600268 }, "steps_from_proto": { "total": 32.45944451699256, "count": 18191, "is_parallel": true, "self": 5.866420379932379, "children": { "_process_rank_one_or_two_observation": { "total": 26.593024137060183, "count": 181910, "is_parallel": true, "self": 26.593024137060183 } } } } } } } } } } }, "trainer_advance": { "total": 124.25629596702015, "count": 18192, "self": 0.46775512802651065, "children": { "process_trajectory": { "total": 27.547039527993775, "count": 18192, "self": 27.004741887993987, "children": { "RLTrainer._checkpoint": { "total": 0.5422976399997879, "count": 4, "self": 0.5422976399997879 } } }, "_update_policy": { "total": 96.24150131099987, "count": 90, "self": 38.56825686999355, "children": { "TorchPPOOptimizer.update": { "total": 57.67324444100632, "count": 4587, "self": 57.67324444100632 } } } } } } }, "trainer_threads": { "total": 7.500000265281415e-07, "count": 1, "self": 7.500000265281415e-07 }, "TrainerController._save_models": { "total": 0.08994876700012355, "count": 1, "self": 0.0008765570003106404, "children": { "RLTrainer._checkpoint": { "total": 0.08907220999981291, "count": 1, "self": 0.08907220999981291 } } } } } } }