{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0919021368026733, "min": 1.0919021368026733, "max": 2.8718159198760986, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10413.470703125, "min": 10413.470703125, "max": 29378.677734375, "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": 12.205342292785645, "min": 0.32794323563575745, "max": 12.205342292785645, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2380.041748046875, "min": 63.62098693847656, "max": 2453.032958984375, "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": 0.07206723039488162, "min": 0.063662699201029, "max": 0.07418873627290279, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2882689215795265, "min": 0.254650796804116, "max": 0.36990817307927426, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19978574787576991, "min": 0.1317103758577586, "max": 0.2864143833079759, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7991429915030797, "min": 0.5268415034310344, "max": 1.3952587837097692, "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": 24.045454545454547, "min": 3.7954545454545454, "max": 24.09090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1058.0, "min": 167.0, "max": 1325.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.045454545454547, "min": 3.7954545454545454, "max": 24.09090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1058.0, "min": 167.0, "max": 1325.0, "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": "1691026063", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1691026532" }, "total": 468.8080965260001, "count": 1, "self": 0.4371717929999477, "children": { "run_training.setup": { "total": 0.04401449500005583, "count": 1, "self": 0.04401449500005583 }, "TrainerController.start_learning": { "total": 468.3269102380001, "count": 1, "self": 0.5492553209924154, "children": { "TrainerController._reset_env": { "total": 6.370661489999975, "count": 1, "self": 6.370661489999975 }, "TrainerController.advance": { "total": 461.2668185330075, "count": 18199, "self": 0.2605864760047325, "children": { "env_step": { "total": 461.00623205700276, "count": 18199, "self": 338.1891974329907, "children": { "SubprocessEnvManager._take_step": { "total": 122.5491257410057, "count": 18199, "self": 1.697311537996029, "children": { "TorchPolicy.evaluate": { "total": 120.85181420300967, "count": 18199, "self": 120.85181420300967 } } }, "workers": { "total": 0.2679088830063847, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 466.7269492059912, "count": 18199, "is_parallel": true, "self": 220.8572072269883, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007014021000031789, "count": 1, "is_parallel": true, "self": 0.004685324999968543, "children": { "_process_rank_one_or_two_observation": { "total": 0.002328696000063246, "count": 10, "is_parallel": true, "self": 0.002328696000063246 } } }, "UnityEnvironment.step": { "total": 0.03540059699992071, "count": 1, "is_parallel": true, "self": 0.00039216599998326274, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003667629999881683, "count": 1, "is_parallel": true, "self": 0.0003667629999881683 }, "communicator.exchange": { "total": 0.03251359099999718, "count": 1, "is_parallel": true, "self": 0.03251359099999718 }, "steps_from_proto": { "total": 0.0021280769999521, "count": 1, "is_parallel": true, "self": 0.0003943170000866303, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017337599998654696, "count": 10, "is_parallel": true, "self": 0.0017337599998654696 } } } } } } }, "UnityEnvironment.step": { "total": 245.86974197900292, "count": 18198, "is_parallel": true, "self": 10.282672206991833, "children": { "UnityEnvironment._generate_step_input": { "total": 5.200049795001519, "count": 18198, "is_parallel": true, "self": 5.200049795001519 }, "communicator.exchange": { "total": 195.13692453400859, "count": 18198, "is_parallel": true, "self": 195.13692453400859 }, "steps_from_proto": { "total": 35.25009544300099, "count": 18198, "is_parallel": true, "self": 6.368682779991104, "children": { "_process_rank_one_or_two_observation": { "total": 28.881412663009883, "count": 181980, "is_parallel": true, "self": 28.881412663009883 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.812300019490067e-05, "count": 1, "self": 3.812300019490067e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 457.8798561490679, "count": 419109, "is_parallel": true, "self": 9.302510940054617, "children": { "process_trajectory": { "total": 247.7934828320133, "count": 419109, "is_parallel": true, "self": 247.10215578501345, "children": { "RLTrainer._checkpoint": { "total": 0.6913270469998452, "count": 4, "is_parallel": true, "self": 0.6913270469998452 } } }, "_update_policy": { "total": 200.783862377, "count": 90, "is_parallel": true, "self": 83.53291189899699, "children": { "TorchPPOOptimizer.update": { "total": 117.250950478003, "count": 4587, "is_parallel": true, "self": 117.250950478003 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14013677100001587, "count": 1, "self": 0.0008861539999998058, "children": { "RLTrainer._checkpoint": { "total": 0.13925061700001606, "count": 1, "self": 0.13925061700001606 } } } } } } }