{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9407172799110413, "min": 0.9407172799110413, "max": 2.865400552749634, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8981.96875, "min": 8981.96875, "max": 29313.046875, "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": 13.18151569366455, "min": 0.478910893201828, "max": 13.18151569366455, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2570.3955078125, "min": 92.9087142944336, "max": 2669.3486328125, "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": 0.06872723592638139, "min": 0.06160516477778882, "max": 0.07452307503234468, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27490894370552554, "min": 0.2464206591111553, "max": 0.3720186086532468, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19583882281885429, "min": 0.1522426145931925, "max": 0.2939532337819829, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7833552912754171, "min": 0.60897045837277, "max": 1.4697661689099144, "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": 26.113636363636363, "min": 4.113636363636363, "max": 26.113636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1149.0, "min": 181.0, "max": 1422.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.113636363636363, "min": 4.113636363636363, "max": 26.113636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1149.0, "min": 181.0, "max": 1422.0, "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": "1675783692", "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": "1.21.6", "end_time_seconds": "1675784275" }, "total": 582.793061588, "count": 1, "self": 0.6414218180000262, "children": { "run_training.setup": { "total": 0.13616364500001055, "count": 1, "self": 0.13616364500001055 }, "TrainerController.start_learning": { "total": 582.015476125, "count": 1, "self": 0.849861700000929, "children": { "TrainerController._reset_env": { "total": 5.785750480000019, "count": 1, "self": 5.785750480000019 }, "TrainerController.advance": { "total": 575.238165143999, "count": 18202, "self": 0.4562970020018611, "children": { "env_step": { "total": 574.7818681419972, "count": 18202, "self": 448.91501897099624, "children": { "SubprocessEnvManager._take_step": { "total": 125.46154358600145, "count": 18202, "self": 2.290974224000763, "children": { "TorchPolicy.evaluate": { "total": 123.17056936200069, "count": 18202, "self": 20.78307281400066, "children": { "TorchPolicy.sample_actions": { "total": 102.38749654800003, "count": 18202, "self": 102.38749654800003 } } } } }, "workers": { "total": 0.4053055849994962, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 579.9443557000013, "count": 18202, "is_parallel": true, "self": 253.54797988199982, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00665506299998242, "count": 1, "is_parallel": true, "self": 0.002790637000003926, "children": { "_process_rank_one_or_two_observation": { "total": 0.0038644259999784936, "count": 10, "is_parallel": true, "self": 0.0038644259999784936 } } }, "UnityEnvironment.step": { "total": 0.04426517000001695, "count": 1, "is_parallel": true, "self": 0.0007279180000239194, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004807319999997617, "count": 1, "is_parallel": true, "self": 0.0004807319999997617 }, "communicator.exchange": { "total": 0.040503462000003765, "count": 1, "is_parallel": true, "self": 0.040503462000003765 }, "steps_from_proto": { "total": 0.0025530579999895053, "count": 1, "is_parallel": true, "self": 0.0005127930000128345, "children": { "_process_rank_one_or_two_observation": { "total": 0.002040264999976671, "count": 10, "is_parallel": true, "self": 0.002040264999976671 } } } } } } }, "UnityEnvironment.step": { "total": 326.3963758180015, "count": 18201, "is_parallel": true, "self": 14.027636195995342, "children": { "UnityEnvironment._generate_step_input": { "total": 7.417946503005908, "count": 18201, "is_parallel": true, "self": 7.417946503005908 }, "communicator.exchange": { "total": 259.8025749330007, "count": 18201, "is_parallel": true, "self": 259.8025749330007 }, "steps_from_proto": { "total": 45.14821818599955, "count": 18201, "is_parallel": true, "self": 10.331911870001875, "children": { "_process_rank_one_or_two_observation": { "total": 34.81630631599768, "count": 182010, "is_parallel": true, "self": 34.81630631599768 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018342399994253356, "count": 1, "self": 0.00018342399994253356, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 569.1125332949963, "count": 673729, "is_parallel": true, "self": 17.43754573400372, "children": { "process_trajectory": { "total": 315.0818943509925, "count": 673729, "is_parallel": true, "self": 314.18629814299254, "children": { "RLTrainer._checkpoint": { "total": 0.8955962079999722, "count": 4, "is_parallel": true, "self": 0.8955962079999722 } } }, "_update_policy": { "total": 236.59309321000012, "count": 90, "is_parallel": true, "self": 79.01853893000035, "children": { "TorchPPOOptimizer.update": { "total": 157.57455427999977, "count": 4587, "is_parallel": true, "self": 157.57455427999977 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14151537700001882, "count": 1, "self": 0.0015476309999939986, "children": { "RLTrainer._checkpoint": { "total": 0.13996774600002482, "count": 1, "self": 0.13996774600002482 } } } } } } }