{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.939903974533081, "min": 0.939903974533081, "max": 2.8618061542510986, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8984.5419921875, "min": 8984.5419921875, "max": 29307.7578125, "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": 12.652807235717773, "min": 0.4648849368095398, "max": 12.652807235717773, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2467.29736328125, "min": 90.18767547607422, "max": 2555.78076171875, "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": 0.06574728134207772, "min": 0.06214581485620846, "max": 0.0759417287732575, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26298912536831087, "min": 0.25861213034313196, "max": 0.3623128241109525, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2067206675077186, "min": 0.13852559327485733, "max": 0.3003142127219368, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8268826700308743, "min": 0.5541023730994293, "max": 1.5015710636096842, "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": 25.068181818181817, "min": 3.8181818181818183, "max": 25.136363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1103.0, "min": 168.0, "max": 1360.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.068181818181817, "min": 3.8181818181818183, "max": 25.136363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1103.0, "min": 168.0, "max": 1360.0, "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": "1686117721", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "0.31.0.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": "1686118200" }, "total": 479.0693589760001, "count": 1, "self": 0.4342586300001585, "children": { "run_training.setup": { "total": 0.04308152099997642, "count": 1, "self": 0.04308152099997642 }, "TrainerController.start_learning": { "total": 478.59201882499997, "count": 1, "self": 0.582145847008178, "children": { "TrainerController._reset_env": { "total": 4.820198939999955, "count": 1, "self": 4.820198939999955 }, "TrainerController.advance": { "total": 473.05334639999205, "count": 18201, "self": 0.2826556329923733, "children": { "env_step": { "total": 472.7706907669997, "count": 18201, "self": 347.00089980400753, "children": { "SubprocessEnvManager._take_step": { "total": 125.47642089000283, "count": 18201, "self": 1.9959155389926764, "children": { "TorchPolicy.evaluate": { "total": 123.48050535101015, "count": 18201, "self": 123.48050535101015 } } }, "workers": { "total": 0.29337007298931894, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 477.01105741001265, "count": 18201, "is_parallel": true, "self": 221.39004880703396, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005056998999862117, "count": 1, "is_parallel": true, "self": 0.0035981340001853823, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014588649996767344, "count": 10, "is_parallel": true, "self": 0.0014588649996767344 } } }, "UnityEnvironment.step": { "total": 0.12518275599995832, "count": 1, "is_parallel": true, "self": 0.0007464570001047832, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004323009998188354, "count": 1, "is_parallel": true, "self": 0.0004323009998188354 }, "communicator.exchange": { "total": 0.12167562100012219, "count": 1, "is_parallel": true, "self": 0.12167562100012219 }, "steps_from_proto": { "total": 0.002328376999912507, "count": 1, "is_parallel": true, "self": 0.0004491740000958089, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018792029998166981, "count": 10, "is_parallel": true, "self": 0.0018792029998166981 } } } } } } }, "UnityEnvironment.step": { "total": 255.6210086029787, "count": 18200, "is_parallel": true, "self": 10.659530684967876, "children": { "UnityEnvironment._generate_step_input": { "total": 5.38152737700716, "count": 18200, "is_parallel": true, "self": 5.38152737700716 }, "communicator.exchange": { "total": 203.93428205699638, "count": 18200, "is_parallel": true, "self": 203.93428205699638 }, "steps_from_proto": { "total": 35.645668484007274, "count": 18200, "is_parallel": true, "self": 6.579969744023174, "children": { "_process_rank_one_or_two_observation": { "total": 29.0656987399841, "count": 182000, "is_parallel": true, "self": 29.0656987399841 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001262039997982356, "count": 1, "self": 0.0001262039997982356, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 469.562286357992, "count": 459537, "is_parallel": true, "self": 9.813155864895407, "children": { "process_trajectory": { "total": 256.492308943097, "count": 459537, "is_parallel": true, "self": 255.08529012109716, "children": { "RLTrainer._checkpoint": { "total": 1.4070188219998272, "count": 4, "is_parallel": true, "self": 1.4070188219998272 } } }, "_update_policy": { "total": 203.2568215499996, "count": 90, "is_parallel": true, "self": 77.77149095499635, "children": { "TorchPPOOptimizer.update": { "total": 125.48533059500323, "count": 4584, "is_parallel": true, "self": 125.48533059500323 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13620143399998597, "count": 1, "self": 0.0008588030000282743, "children": { "RLTrainer._checkpoint": { "total": 0.1353426309999577, "count": 1, "self": 0.1353426309999577 } } } } } } }