{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9566552639007568, "min": 0.9566552639007568, "max": 2.8713760375976562, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9176.2373046875, "min": 9176.2373046875, "max": 29405.76171875, "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": 12.648460388183594, "min": 0.30620867013931274, "max": 12.648460388183594, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2466.44970703125, "min": 59.40447998046875, "max": 2561.74951171875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06920844104281379, "min": 0.061240087579633326, "max": 0.07508737799693263, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27683376417125516, "min": 0.25467945404770764, "max": 0.3754368899846632, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20159733434226, "min": 0.0921685480667899, "max": 0.28262753375605043, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.80638933736904, "min": 0.3686741922671596, "max": 1.394185670450622, "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": 25.181818181818183, "min": 2.659090909090909, "max": 25.181818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1108.0, "min": 117.0, "max": 1369.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.181818181818183, "min": 2.659090909090909, "max": 25.181818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1108.0, "min": 117.0, "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": "1697690511", "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": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697690965" }, "total": 453.960291537, "count": 1, "self": 0.7281073500000161, "children": { "run_training.setup": { "total": 0.050372611000000234, "count": 1, "self": 0.050372611000000234 }, "TrainerController.start_learning": { "total": 453.181811576, "count": 1, "self": 0.5454827080112636, "children": { "TrainerController._reset_env": { "total": 8.128453510999975, "count": 1, "self": 8.128453510999975 }, "TrainerController.advance": { "total": 444.37064995298874, "count": 18211, "self": 0.2499853339808169, "children": { "env_step": { "total": 444.1206646190079, "count": 18211, "self": 302.6569784720113, "children": { "SubprocessEnvManager._take_step": { "total": 141.19078231600218, "count": 18211, "self": 1.3771694500095464, "children": { "TorchPolicy.evaluate": { "total": 139.81361286599264, "count": 18211, "self": 139.81361286599264 } } }, "workers": { "total": 0.27290383099443716, "count": 18211, "self": 0.0, "children": { "worker_root": { "total": 451.91614313199494, "count": 18211, "is_parallel": true, "self": 219.28228060300341, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005717715000002954, "count": 1, "is_parallel": true, "self": 0.004302284999994299, "children": { "_process_rank_one_or_two_observation": { "total": 0.001415430000008655, "count": 10, "is_parallel": true, "self": 0.001415430000008655 } } }, "UnityEnvironment.step": { "total": 0.06616440899995268, "count": 1, "is_parallel": true, "self": 0.0006112269999789532, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003992549999907169, "count": 1, "is_parallel": true, "self": 0.0003992549999907169 }, "communicator.exchange": { "total": 0.06313014500000236, "count": 1, "is_parallel": true, "self": 0.06313014500000236 }, "steps_from_proto": { "total": 0.002023781999980656, "count": 1, "is_parallel": true, "self": 0.0004056659998354917, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016181160001451644, "count": 10, "is_parallel": true, "self": 0.0016181160001451644 } } } } } } }, "UnityEnvironment.step": { "total": 232.63386252899153, "count": 18210, "is_parallel": true, "self": 10.336369648001721, "children": { "UnityEnvironment._generate_step_input": { "total": 5.222083172991859, "count": 18210, "is_parallel": true, "self": 5.222083172991859 }, "communicator.exchange": { "total": 184.1619749119987, "count": 18210, "is_parallel": true, "self": 184.1619749119987 }, "steps_from_proto": { "total": 32.91343479599925, "count": 18210, "is_parallel": true, "self": 6.111375260013972, "children": { "_process_rank_one_or_two_observation": { "total": 26.80205953598528, "count": 182100, "is_parallel": true, "self": 26.80205953598528 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012111900002764742, "count": 1, "self": 0.00012111900002764742, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 440.6075587529629, "count": 468517, "is_parallel": true, "self": 9.840416043959294, "children": { "process_trajectory": { "total": 248.75448957500413, "count": 468517, "is_parallel": true, "self": 247.7176520210042, "children": { "RLTrainer._checkpoint": { "total": 1.0368375539999306, "count": 4, "is_parallel": true, "self": 1.0368375539999306 } } }, "_update_policy": { "total": 182.0126531339995, "count": 90, "is_parallel": true, "self": 55.247067512998456, "children": { "TorchPPOOptimizer.update": { "total": 126.76558562100104, "count": 4584, "is_parallel": true, "self": 126.76558562100104 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13710428499996397, "count": 1, "self": 0.0011133140000083586, "children": { "RLTrainer._checkpoint": { "total": 0.1359909709999556, "count": 1, "self": 0.1359909709999556 } } } } } } }