{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9852144718170166, "min": 0.9852144718170166, "max": 2.8514280319213867, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9439.33984375, "min": 9439.33984375, "max": 29170.109375, "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": 12.977479934692383, "min": 0.26372748613357544, "max": 12.977479934692383, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2530.608642578125, "min": 51.16313171386719, "max": 2624.497314453125, "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": 0.07261852280570048, "min": 0.06043794525555545, "max": 0.07658873598568379, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29047409122280193, "min": 0.2417517810222218, "max": 0.38294367992841893, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19275300014837116, "min": 0.12502424285847547, "max": 0.30128537571313335, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7710120005934846, "min": 0.5000969714339019, "max": 1.4998737848272512, "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": 26.045454545454547, "min": 3.409090909090909, "max": 26.045454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1146.0, "min": 150.0, "max": 1392.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.045454545454547, "min": 3.409090909090909, "max": 26.045454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1146.0, "min": 150.0, "max": 1392.0, "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": "1677957485", "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": "1677957925" }, "total": 439.80674753300013, "count": 1, "self": 0.5827865149999525, "children": { "run_training.setup": { "total": 0.1146797169999445, "count": 1, "self": 0.1146797169999445 }, "TrainerController.start_learning": { "total": 439.10928130100024, "count": 1, "self": 0.49013238002430626, "children": { "TrainerController._reset_env": { "total": 9.870593473999861, "count": 1, "self": 9.870593473999861 }, "TrainerController.advance": { "total": 428.5568411649763, "count": 18220, "self": 0.25617263796334555, "children": { "env_step": { "total": 428.30066852701293, "count": 18220, "self": 292.4814691130073, "children": { "SubprocessEnvManager._take_step": { "total": 135.5665108149883, "count": 18220, "self": 1.426672766975571, "children": { "TorchPolicy.evaluate": { "total": 134.13983804801273, "count": 18220, "self": 29.04588160496678, "children": { "TorchPolicy.sample_actions": { "total": 105.09395644304595, "count": 18220, "self": 105.09395644304595 } } } } }, "workers": { "total": 0.25268859901734686, "count": 18220, "self": 0.0, "children": { "worker_root": { "total": 437.60509621400047, "count": 18220, "is_parallel": true, "self": 214.271264778022, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0053425359999437205, "count": 1, "is_parallel": true, "self": 0.003912337999736337, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014301980002073833, "count": 10, "is_parallel": true, "self": 0.0014301980002073833 } } }, "UnityEnvironment.step": { "total": 0.05313780200003748, "count": 1, "is_parallel": true, "self": 0.0004176479999387084, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030070299999351846, "count": 1, "is_parallel": true, "self": 0.00030070299999351846 }, "communicator.exchange": { "total": 0.05097143800003323, "count": 1, "is_parallel": true, "self": 0.05097143800003323 }, "steps_from_proto": { "total": 0.0014480130000720237, "count": 1, "is_parallel": true, "self": 0.00034074200038958224, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011072709996824415, "count": 10, "is_parallel": true, "self": 0.0011072709996824415 } } } } } } }, "UnityEnvironment.step": { "total": 223.33383143597848, "count": 18219, "is_parallel": true, "self": 9.141704983982436, "children": { "UnityEnvironment._generate_step_input": { "total": 5.043984282015117, "count": 18219, "is_parallel": true, "self": 5.043984282015117 }, "communicator.exchange": { "total": 179.68728709097036, "count": 18219, "is_parallel": true, "self": 179.68728709097036 }, "steps_from_proto": { "total": 29.46085507901057, "count": 18219, "is_parallel": true, "self": 6.263779386135184, "children": { "_process_rank_one_or_two_observation": { "total": 23.197075692875387, "count": 182190, "is_parallel": true, "self": 23.197075692875387 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013717000001634005, "count": 1, "self": 0.00013717000001634005, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 425.36782665592455, "count": 391963, "is_parallel": true, "self": 9.727450885914095, "children": { "process_trajectory": { "total": 243.6404928080101, "count": 391963, "is_parallel": true, "self": 242.3490964820096, "children": { "RLTrainer._checkpoint": { "total": 1.2913963260004948, "count": 4, "is_parallel": true, "self": 1.2913963260004948 } } }, "_update_policy": { "total": 171.99988296200036, "count": 90, "is_parallel": true, "self": 60.731267792992185, "children": { "TorchPPOOptimizer.update": { "total": 111.26861516900817, "count": 4581, "is_parallel": true, "self": 111.26861516900817 } } } } } } } } }, "TrainerController._save_models": { "total": 0.19157711199977712, "count": 1, "self": 0.0011026090000996192, "children": { "RLTrainer._checkpoint": { "total": 0.1904745029996775, "count": 1, "self": 0.1904745029996775 } } } } } } }