{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9603326916694641, "min": 0.9603326916694641, "max": 2.8567922115325928, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9179.8203125, "min": 9179.8203125, "max": 29224.984375, "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": 12.717241287231445, "min": 0.3215433359146118, "max": 12.744430541992188, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2479.862060546875, "min": 62.37940979003906, "max": 2599.86376953125, "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": 0.07218304525525251, "min": 0.06349265968824244, "max": 0.07601231713984709, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28873218102101006, "min": 0.25397063875296977, "max": 0.3800615856992354, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22053762627582923, "min": 0.12940830391073854, "max": 0.279894048852079, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8821505051033169, "min": 0.5176332156429542, "max": 1.399470244260395, "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": 24.727272727272727, "min": 3.6818181818181817, "max": 25.381818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1088.0, "min": 162.0, "max": 1396.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.727272727272727, "min": 3.6818181818181817, "max": 25.381818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1088.0, "min": 162.0, "max": 1396.0, "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": "1703600463", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703600980" }, "total": 516.4217766039999, "count": 1, "self": 0.44424547999994957, "children": { "run_training.setup": { "total": 0.05911806400001751, "count": 1, "self": 0.05911806400001751 }, "TrainerController.start_learning": { "total": 515.9184130599999, "count": 1, "self": 0.6264965709934813, "children": { "TrainerController._reset_env": { "total": 3.1103843359999814, "count": 1, "self": 3.1103843359999814 }, "TrainerController.advance": { "total": 512.0797487670065, "count": 18200, "self": 0.31635533700949736, "children": { "env_step": { "total": 511.76339342999705, "count": 18200, "self": 340.7622800939897, "children": { "SubprocessEnvManager._take_step": { "total": 170.67137533299433, "count": 18200, "self": 1.6605838339864931, "children": { "TorchPolicy.evaluate": { "total": 169.01079149900784, "count": 18200, "self": 169.01079149900784 } } }, "workers": { "total": 0.3297380030130057, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 514.3228979090011, "count": 18200, "is_parallel": true, "self": 251.1353509249996, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004943920000016533, "count": 1, "is_parallel": true, "self": 0.0036309570000980784, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013129629999184544, "count": 10, "is_parallel": true, "self": 0.0013129629999184544 } } }, "UnityEnvironment.step": { "total": 0.04572441299995944, "count": 1, "is_parallel": true, "self": 0.0008333389998824714, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004647260000183451, "count": 1, "is_parallel": true, "self": 0.0004647260000183451 }, "communicator.exchange": { "total": 0.041280020000044715, "count": 1, "is_parallel": true, "self": 0.041280020000044715 }, "steps_from_proto": { "total": 0.0031463280000139093, "count": 1, "is_parallel": true, "self": 0.0007483290000322995, "children": { "_process_rank_one_or_two_observation": { "total": 0.00239799899998161, "count": 10, "is_parallel": true, "self": 0.00239799899998161 } } } } } } }, "UnityEnvironment.step": { "total": 263.1875469840015, "count": 18199, "is_parallel": true, "self": 12.037682898015305, "children": { "UnityEnvironment._generate_step_input": { "total": 6.237391424989369, "count": 18199, "is_parallel": true, "self": 6.237391424989369 }, "communicator.exchange": { "total": 204.8267996400046, "count": 18199, "is_parallel": true, "self": 204.8267996400046 }, "steps_from_proto": { "total": 40.0856730209922, "count": 18199, "is_parallel": true, "self": 7.623511413978463, "children": { "_process_rank_one_or_two_observation": { "total": 32.46216160701374, "count": 181990, "is_parallel": true, "self": 32.46216160701374 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013976599996112782, "count": 1, "self": 0.00013976599996112782, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 505.2498369130649, "count": 741837, "is_parallel": true, "self": 16.81447420497875, "children": { "process_trajectory": { "total": 279.29904887308595, "count": 741837, "is_parallel": true, "self": 278.4310363470858, "children": { "RLTrainer._checkpoint": { "total": 0.8680125260001432, "count": 4, "is_parallel": true, "self": 0.8680125260001432 } } }, "_update_policy": { "total": 209.13631383500018, "count": 90, "is_parallel": true, "self": 67.42209046999625, "children": { "TorchPPOOptimizer.update": { "total": 141.71422336500393, "count": 4581, "is_parallel": true, "self": 141.71422336500393 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10164362000000438, "count": 1, "self": 0.000993566000033752, "children": { "RLTrainer._checkpoint": { "total": 0.10065005399997062, "count": 1, "self": 0.10065005399997062 } } } } } } }