{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8825687766075134, "min": 0.8825687766075134, "max": 2.8568341732025146, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8426.7666015625, "min": 8426.7666015625, "max": 29256.837890625, "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": 13.202091217041016, "min": 0.3778069019317627, "max": 13.202091217041016, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2574.40771484375, "min": 73.29454040527344, "max": 2684.656005859375, "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": 0.06981618750424054, "min": 0.061968649662580276, "max": 0.07922804611934778, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27926475001696216, "min": 0.2555737284607911, "max": 0.36008175204401865, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18397020504755132, "min": 0.13115806292797275, "max": 0.3092269118071771, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7358808201902053, "min": 0.524632251711891, "max": 1.4609897291543437, "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": 25.931818181818183, "min": 3.5454545454545454, "max": 26.09090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1141.0, "min": 156.0, "max": 1435.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.931818181818183, "min": 3.5454545454545454, "max": 26.09090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1141.0, "min": 156.0, "max": 1435.0, "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": "1704187274", "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": "1704187746" }, "total": 472.1103332120001, "count": 1, "self": 0.44418246000032013, "children": { "run_training.setup": { "total": 0.05086885099990468, "count": 1, "self": 0.05086885099990468 }, "TrainerController.start_learning": { "total": 471.6152819009999, "count": 1, "self": 0.5907592580356322, "children": { "TrainerController._reset_env": { "total": 4.020234241999788, "count": 1, "self": 4.020234241999788 }, "TrainerController.advance": { "total": 466.9121249369646, "count": 18199, "self": 0.2884589669820343, "children": { "env_step": { "total": 466.62366596998254, "count": 18199, "self": 307.44848980798406, "children": { "SubprocessEnvManager._take_step": { "total": 158.8754533829865, "count": 18199, "self": 1.6710524220111438, "children": { "TorchPolicy.evaluate": { "total": 157.20440096097536, "count": 18199, "self": 157.20440096097536 } } }, "workers": { "total": 0.2997227790119723, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 470.2723428979798, "count": 18199, "is_parallel": true, "self": 233.61832031398126, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004594067000198265, "count": 1, "is_parallel": true, "self": 0.0030997379990367335, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014943290011615318, "count": 10, "is_parallel": true, "self": 0.0014943290011615318 } } }, "UnityEnvironment.step": { "total": 0.07580146700001933, "count": 1, "is_parallel": true, "self": 0.0006557440001415671, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004493940000429575, "count": 1, "is_parallel": true, "self": 0.0004493940000429575 }, "communicator.exchange": { "total": 0.07246296499988603, "count": 1, "is_parallel": true, "self": 0.07246296499988603 }, "steps_from_proto": { "total": 0.0022333639999487787, "count": 1, "is_parallel": true, "self": 0.0004351810007392487, "children": { "_process_rank_one_or_two_observation": { "total": 0.00179818299920953, "count": 10, "is_parallel": true, "self": 0.00179818299920953 } } } } } } }, "UnityEnvironment.step": { "total": 236.65402258399854, "count": 18198, "is_parallel": true, "self": 11.283207996012607, "children": { "UnityEnvironment._generate_step_input": { "total": 5.837522689962498, "count": 18198, "is_parallel": true, "self": 5.837522689962498 }, "communicator.exchange": { "total": 182.96531935998973, "count": 18198, "is_parallel": true, "self": 182.96531935998973 }, "steps_from_proto": { "total": 36.5679725380337, "count": 18198, "is_parallel": true, "self": 6.838243260046056, "children": { "_process_rank_one_or_two_observation": { "total": 29.729729277987644, "count": 181980, "is_parallel": true, "self": 29.729729277987644 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019311899995955173, "count": 1, "self": 0.00019311899995955173, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 461.0351080338887, "count": 685956, "is_parallel": true, "self": 14.953992850999839, "children": { "process_trajectory": { "total": 255.6252552998917, "count": 685956, "is_parallel": true, "self": 254.98932087889125, "children": { "RLTrainer._checkpoint": { "total": 0.6359344210004565, "count": 4, "is_parallel": true, "self": 0.6359344210004565 } } }, "_update_policy": { "total": 190.45585988299717, "count": 90, "is_parallel": true, "self": 61.31826781401196, "children": { "TorchPPOOptimizer.update": { "total": 129.1375920689852, "count": 4587, "is_parallel": true, "self": 129.1375920689852 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09197034499993606, "count": 1, "self": 0.0009793029998945713, "children": { "RLTrainer._checkpoint": { "total": 0.09099104200004149, "count": 1, "self": 0.09099104200004149 } } } } } } }