{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.867946147918701, "min": 2.867946147918701, "max": 2.867946147918701, "count": 1 }, "SnowballTarget.Policy.Entropy.sum": { "value": 29433.732421875, "min": 29433.732421875, "max": 29433.732421875, "count": 1 }, "SnowballTarget.Step.mean": { "value": 9952.0, "min": 9952.0, "max": 9952.0, "count": 1 }, "SnowballTarget.Step.sum": { "value": 9952.0, "min": 9952.0, "max": 9952.0, "count": 1 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 0.36501964926719666, "min": 0.36501964926719666, "max": 0.36501964926719666, "count": 1 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 70.81381225585938, "min": 70.81381225585938, "max": 70.81381225585938, "count": 1 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 1 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 8756.0, "count": 1 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06009695729764586, "min": 0.06009695729764586, "max": 0.06009695729764586, "count": 1 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24038782919058344, "min": 0.24038782919058344, "max": 0.24038782919058344, "count": 1 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.11938250649209116, "min": 0.11938250649209116, "max": 0.11938250649209116, "count": 1 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.47753002596836464, "min": 0.47753002596836464, "max": 0.47753002596836464, "count": 1 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.000291882002706, "min": 0.000291882002706, "max": 0.000291882002706, "count": 1 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.001167528010824, "min": 0.001167528010824, "max": 0.001167528010824, "count": 1 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.19729400000000002, "min": 0.19729400000000002, "max": 0.19729400000000002, "count": 1 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.7891760000000001, "min": 0.7891760000000001, "max": 0.7891760000000001, "count": 1 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0048649706, "min": 0.0048649706, "max": 0.0048649706, "count": 1 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0194598824, "min": 0.0194598824, "max": 0.0194598824, "count": 1 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 3.6136363636363638, "min": 3.6136363636363638, "max": 3.6136363636363638, "count": 1 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 159.0, "min": 159.0, "max": 159.0, "count": 1 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 3.6136363636363638, "min": 3.6136363636363638, "max": 3.6136363636363638, "count": 1 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 159.0, "min": 159.0, "max": 159.0, "count": 1 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679087839", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1679087877" }, "total": 37.19952396700006, "count": 1, "self": 0.18337441200009152, "children": { "run_training.setup": { "total": 0.10661946999999827, "count": 1, "self": 0.10661946999999827 }, "TrainerController.start_learning": { "total": 36.90953008499997, "count": 1, "self": 0.14344037400132947, "children": { "TrainerController._reset_env": { "total": 10.20520952999999, "count": 1, "self": 10.20520952999999 }, "TrainerController.advance": { "total": 26.113130139998702, "count": 1073, "self": 0.015438158999131701, "children": { "env_step": { "total": 26.09769198099957, "count": 1073, "self": 19.096851784999217, "children": { "SubprocessEnvManager._take_step": { "total": 6.985853050999594, "count": 1073, "self": 0.20996643500183154, "children": { "TorchPolicy.evaluate": { "total": 6.775886615997763, "count": 1073, "self": 6.775886615997763 } } }, "workers": { "total": 0.014987145000759483, "count": 1072, "self": 0.0, "children": { "worker_root": { "total": 36.362026185999696, "count": 1072, "is_parallel": true, "self": 22.53656574799936, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00622794100002011, "count": 1, "is_parallel": true, "self": 0.0047879080000825525, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014400329999375572, "count": 10, "is_parallel": true, "self": 0.0014400329999375572 } } }, "UnityEnvironment.step": { "total": 0.04782305899999528, "count": 1, "is_parallel": true, "self": 0.0006204030000276362, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00027903400001605405, "count": 1, "is_parallel": true, "self": 0.00027903400001605405 }, "communicator.exchange": { "total": 0.04514546299998301, "count": 1, "is_parallel": true, "self": 0.04514546299998301 }, "steps_from_proto": { "total": 0.001778158999968582, "count": 1, "is_parallel": true, "self": 0.0003690989998972327, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014090600000713494, "count": 10, "is_parallel": true, "self": 0.0014090600000713494 } } } } } } }, "UnityEnvironment.step": { "total": 13.825460438000334, "count": 1071, "is_parallel": true, "self": 0.5667811729985033, "children": { "UnityEnvironment._generate_step_input": { "total": 0.30566426999985197, "count": 1071, "is_parallel": true, "self": 0.30566426999985197 }, "communicator.exchange": { "total": 11.150007539001876, "count": 1071, "is_parallel": true, "self": 11.150007539001876 }, "steps_from_proto": { "total": 1.8030074560001026, "count": 1071, "is_parallel": true, "self": 0.3532421949989839, "children": { "_process_rank_one_or_two_observation": { "total": 1.4497652610011187, "count": 10710, "is_parallel": true, "self": 1.4497652610011187 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011445600000570266, "count": 1, "self": 0.00011445600000570266, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 26.023509298995577, "count": 22192, "is_parallel": true, "self": 0.5657549129856534, "children": { "process_trajectory": { "total": 14.718005123009846, "count": 22192, "is_parallel": true, "self": 14.718005123009846 }, "_update_policy": { "total": 10.739749263000078, "count": 5, "is_parallel": true, "self": 3.8587524820004546, "children": { "TorchPPOOptimizer.update": { "total": 6.880996780999624, "count": 252, "is_parallel": true, "self": 6.880996780999624 } } } } } } } } }, "TrainerController._save_models": { "total": 0.4476355849999436, "count": 1, "self": 0.001131046999944374, "children": { "RLTrainer._checkpoint": { "total": 0.44650453799999923, "count": 1, "self": 0.44650453799999923 } } } } } } }