{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9539257287979126, "min": 0.944949746131897, "max": 2.8588168621063232, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9171.0419921875, "min": 9171.0419921875, "max": 29277.142578125, "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": 12.955326080322266, "min": 0.3800961673259735, "max": 12.969542503356934, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2526.28857421875, "min": 73.73865509033203, "max": 2645.78662109375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07818989367646567, "min": 0.06300880687822606, "max": 0.07818989367646567, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3127595747058627, "min": 0.25203522751290425, "max": 0.366830339158803, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2159982683027492, "min": 0.1555050979642307, "max": 0.29353994470016626, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8639930732109968, "min": 0.6220203918569228, "max": 1.4676997235008313, "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": 25.068181818181817, "min": 3.8181818181818183, "max": 25.672727272727272, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1103.0, "min": 168.0, "max": 1412.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.068181818181817, "min": 3.8181818181818183, "max": 25.672727272727272, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1103.0, "min": 168.0, "max": 1412.0, "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": "1684145603", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684146076" }, "total": 473.354601016, "count": 1, "self": 0.7972571180000045, "children": { "run_training.setup": { "total": 0.04001236599998492, "count": 1, "self": 0.04001236599998492 }, "TrainerController.start_learning": { "total": 472.517331532, "count": 1, "self": 0.5752886390019967, "children": { "TrainerController._reset_env": { "total": 3.681956935999949, "count": 1, "self": 3.681956935999949 }, "TrainerController.advance": { "total": 468.0301189899981, "count": 18217, "self": 0.2781598449894318, "children": { "env_step": { "total": 467.75195914500864, "count": 18217, "self": 342.45576895802066, "children": { "SubprocessEnvManager._take_step": { "total": 125.0085457909966, "count": 18217, "self": 1.8798069289957766, "children": { "TorchPolicy.evaluate": { "total": 123.12873886200083, "count": 18217, "self": 123.12873886200083 } } }, "workers": { "total": 0.2876443959913786, "count": 18217, "self": 0.0, "children": { "worker_root": { "total": 470.7635059569941, "count": 18217, "is_parallel": true, "self": 218.2725130869955, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005924907999997231, "count": 1, "is_parallel": true, "self": 0.004294920999939222, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016299870000580086, "count": 10, "is_parallel": true, "self": 0.0016299870000580086 } } }, "UnityEnvironment.step": { "total": 0.05887442600004533, "count": 1, "is_parallel": true, "self": 0.0006608290000826855, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003481879999753801, "count": 1, "is_parallel": true, "self": 0.0003481879999753801 }, "communicator.exchange": { "total": 0.05478458400000363, "count": 1, "is_parallel": true, "self": 0.05478458400000363 }, "steps_from_proto": { "total": 0.0030808249999836335, "count": 1, "is_parallel": true, "self": 0.0008109189999458977, "children": { "_process_rank_one_or_two_observation": { "total": 0.002269906000037736, "count": 10, "is_parallel": true, "self": 0.002269906000037736 } } } } } } }, "UnityEnvironment.step": { "total": 252.4909928699986, "count": 18216, "is_parallel": true, "self": 9.87830091899582, "children": { "UnityEnvironment._generate_step_input": { "total": 5.540793312001824, "count": 18216, "is_parallel": true, "self": 5.540793312001824 }, "communicator.exchange": { "total": 202.10860533200128, "count": 18216, "is_parallel": true, "self": 202.10860533200128 }, "steps_from_proto": { "total": 34.963293306999674, "count": 18216, "is_parallel": true, "self": 6.842354495980146, "children": { "_process_rank_one_or_two_observation": { "total": 28.120938811019528, "count": 182160, "is_parallel": true, "self": 28.120938811019528 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015193000001545443, "count": 1, "self": 0.00015193000001545443, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 464.4363361579924, "count": 458349, "is_parallel": true, "self": 9.914046796016578, "children": { "process_trajectory": { "total": 254.0779934119755, "count": 458349, "is_parallel": true, "self": 252.56403319497537, "children": { "RLTrainer._checkpoint": { "total": 1.5139602170001467, "count": 4, "is_parallel": true, "self": 1.5139602170001467 } } }, "_update_policy": { "total": 200.4442959500003, "count": 90, "is_parallel": true, "self": 78.93493122699971, "children": { "TorchPPOOptimizer.update": { "total": 121.5093647230006, "count": 4587, "is_parallel": true, "self": 121.5093647230006 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2298150369999803, "count": 1, "self": 0.0011373359999424792, "children": { "RLTrainer._checkpoint": { "total": 0.22867770100003781, "count": 1, "self": 0.22867770100003781 } } } } } } }