{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9231085181236267, "min": 0.8955596685409546, "max": 2.859286308288574, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8823.994140625, "min": 8823.994140625, "max": 29439.2109375, "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": 13.036027908325195, "min": 0.4035024642944336, "max": 13.042854309082031, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2542.025390625, "min": 78.27947998046875, "max": 2660.7421875, "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": 0.06676121043796336, "min": 0.05853854003647689, "max": 0.07155164661251583, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26704484175185345, "min": 0.23415416014590756, "max": 0.3557945274903129, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19259400548888186, "min": 0.1326031947768677, "max": 0.3011288558881657, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7703760219555275, "min": 0.5304127791074708, "max": 1.4629737577017616, "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": 25.386363636363637, "min": 4.045454545454546, "max": 25.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1117.0, "min": 178.0, "max": 1397.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.386363636363637, "min": 4.045454545454546, "max": 25.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1117.0, "min": 178.0, "max": 1397.0, "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": "1680243225", "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 --force", "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": "1680243716" }, "total": 490.33022844699985, "count": 1, "self": 0.43094076199986375, "children": { "run_training.setup": { "total": 0.11729972200009797, "count": 1, "self": 0.11729972200009797 }, "TrainerController.start_learning": { "total": 489.7819879629999, "count": 1, "self": 0.5915837049835773, "children": { "TrainerController._reset_env": { "total": 3.6460233909999715, "count": 1, "self": 3.6460233909999715 }, "TrainerController.advance": { "total": 485.4027254380162, "count": 18204, "self": 0.29574892800928865, "children": { "env_step": { "total": 485.1069765100069, "count": 18204, "self": 354.1473724380098, "children": { "SubprocessEnvManager._take_step": { "total": 130.67007167100837, "count": 18204, "self": 1.7646395749982275, "children": { "TorchPolicy.evaluate": { "total": 128.90543209601014, "count": 18204, "self": 128.90543209601014 } } }, "workers": { "total": 0.289532400988719, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 488.0891875000002, "count": 18204, "is_parallel": true, "self": 226.131890452991, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002220807000185232, "count": 1, "is_parallel": true, "self": 0.000665319000290765, "children": { "_process_rank_one_or_two_observation": { "total": 0.001555487999894467, "count": 10, "is_parallel": true, "self": 0.001555487999894467 } } }, "UnityEnvironment.step": { "total": 0.03719217100001515, "count": 1, "is_parallel": true, "self": 0.0006002879997595301, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034497900014685, "count": 1, "is_parallel": true, "self": 0.00034497900014685 }, "communicator.exchange": { "total": 0.03425979200005713, "count": 1, "is_parallel": true, "self": 0.03425979200005713 }, "steps_from_proto": { "total": 0.0019871120000516385, "count": 1, "is_parallel": true, "self": 0.0004004030004125525, "children": { "_process_rank_one_or_two_observation": { "total": 0.001586708999639086, "count": 10, "is_parallel": true, "self": 0.001586708999639086 } } } } } } }, "UnityEnvironment.step": { "total": 261.9572970470092, "count": 18203, "is_parallel": true, "self": 10.499255111009006, "children": { "UnityEnvironment._generate_step_input": { "total": 5.821477181998489, "count": 18203, "is_parallel": true, "self": 5.821477181998489 }, "communicator.exchange": { "total": 210.35119799100517, "count": 18203, "is_parallel": true, "self": 210.35119799100517 }, "steps_from_proto": { "total": 35.285366762996546, "count": 18203, "is_parallel": true, "self": 7.136795424044067, "children": { "_process_rank_one_or_two_observation": { "total": 28.14857133895248, "count": 182030, "is_parallel": true, "self": 28.14857133895248 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013467400003719376, "count": 1, "self": 0.00013467400003719376, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 481.53787640196833, "count": 431864, "is_parallel": true, "self": 11.208973349926964, "children": { "process_trajectory": { "total": 267.89448236804014, "count": 431864, "is_parallel": true, "self": 266.19651484504016, "children": { "RLTrainer._checkpoint": { "total": 1.6979675229999884, "count": 4, "is_parallel": true, "self": 1.6979675229999884 } } }, "_update_policy": { "total": 202.43442068400122, "count": 90, "is_parallel": true, "self": 76.33989167999903, "children": { "TorchPPOOptimizer.update": { "total": 126.0945290040022, "count": 4587, "is_parallel": true, "self": 126.0945290040022 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14152075500010142, "count": 1, "self": 0.0010808670001551945, "children": { "RLTrainer._checkpoint": { "total": 0.14043988799994622, "count": 1, "self": 0.14043988799994622 } } } } } } }