{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.892038881778717, "min": 0.892038881778717, "max": 2.853081703186035, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8517.1875, "min": 8517.1875, "max": 29218.41015625, "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": 13.168224334716797, "min": 0.4111616909503937, "max": 13.184819221496582, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2567.8037109375, "min": 79.76536560058594, "max": 2689.703125, "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": 0.06960944524334456, "min": 0.06563399338242562, "max": 0.07279902097272606, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27843778097337823, "min": 0.2625359735297025, "max": 0.3639951048636303, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17255926596767762, "min": 0.12072218996404176, "max": 0.2944142708883566, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6902370638707105, "min": 0.482888759856167, "max": 1.2868026956039316, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000009e-06, "min": 8.082097306000009e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.2328389224000035e-05, "min": 3.2328389224000035e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269399999999998, "min": 0.10269399999999998, "max": 0.197294, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4107759999999999, "min": 0.4107759999999999, "max": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.004864970599999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.59090909090909, "min": 3.2045454545454546, "max": 25.89090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1126.0, "min": 141.0, "max": 1424.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.59090909090909, "min": 3.2045454545454546, "max": 25.89090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1126.0, "min": 141.0, "max": 1424.0, "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": "1677214323", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677214831" }, "total": 507.8725578900003, "count": 1, "self": 0.3858022100002927, "children": { "run_training.setup": { "total": 0.11497642699987409, "count": 1, "self": 0.11497642699987409 }, "TrainerController.start_learning": { "total": 507.3717792530001, "count": 1, "self": 0.505777959995612, "children": { "TrainerController._reset_env": { "total": 9.831027076999817, "count": 1, "self": 9.831027076999817 }, "TrainerController.advance": { "total": 496.92010923600446, "count": 18200, "self": 0.2607775159749508, "children": { "env_step": { "total": 496.6593317200295, "count": 18200, "self": 361.89644599901067, "children": { "SubprocessEnvManager._take_step": { "total": 134.50254242001256, "count": 18200, "self": 1.4338672299713835, "children": { "TorchPolicy.evaluate": { "total": 133.06867519004118, "count": 18200, "self": 29.480927512062863, "children": { "TorchPolicy.sample_actions": { "total": 103.58774767797831, "count": 18200, "self": 103.58774767797831 } } } } }, "workers": { "total": 0.2603433010062872, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 505.83003653701917, "count": 18200, "is_parallel": true, "self": 275.3312124290683, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008388594000280136, "count": 1, "is_parallel": true, "self": 0.0045375670010798785, "children": { "_process_rank_one_or_two_observation": { "total": 0.0038510269992002577, "count": 10, "is_parallel": true, "self": 0.0038510269992002577 } } }, "UnityEnvironment.step": { "total": 0.04066075600030672, "count": 1, "is_parallel": true, "self": 0.0004776020000463177, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003173640002387401, "count": 1, "is_parallel": true, "self": 0.0003173640002387401 }, "communicator.exchange": { "total": 0.03801045399995928, "count": 1, "is_parallel": true, "self": 0.03801045399995928 }, "steps_from_proto": { "total": 0.0018553360000623798, "count": 1, "is_parallel": true, "self": 0.00042897699950117385, "children": { "_process_rank_one_or_two_observation": { "total": 0.001426359000561206, "count": 10, "is_parallel": true, "self": 0.001426359000561206 } } } } } } }, "UnityEnvironment.step": { "total": 230.4988241079509, "count": 18199, "is_parallel": true, "self": 9.344617819952418, "children": { "UnityEnvironment._generate_step_input": { "total": 5.259446912963085, "count": 18199, "is_parallel": true, "self": 5.259446912963085 }, "communicator.exchange": { "total": 186.04022162900765, "count": 18199, "is_parallel": true, "self": 186.04022162900765 }, "steps_from_proto": { "total": 29.854537746027745, "count": 18199, "is_parallel": true, "self": 6.525459191944719, "children": { "_process_rank_one_or_two_observation": { "total": 23.329078554083026, "count": 181990, "is_parallel": true, "self": 23.329078554083026 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.631800018411013e-05, "count": 1, "self": 3.631800018411013e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 493.7006018827956, "count": 389016, "is_parallel": true, "self": 9.577440201870559, "children": { "process_trajectory": { "total": 248.25652972392572, "count": 389016, "is_parallel": true, "self": 247.52132248892622, "children": { "RLTrainer._checkpoint": { "total": 0.7352072349995069, "count": 4, "is_parallel": true, "self": 0.7352072349995069 } } }, "_update_policy": { "total": 235.8666319569993, "count": 90, "is_parallel": true, "self": 94.20312565501308, "children": { "TorchPPOOptimizer.update": { "total": 141.66350630198622, "count": 7645, "is_parallel": true, "self": 141.66350630198622 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11482866200003627, "count": 1, "self": 0.0009673330000623537, "children": { "RLTrainer._checkpoint": { "total": 0.11386132899997392, "count": 1, "self": 0.11386132899997392 } } } } } } }