{ "name": "root", "gauges": { "Worm.Policy.Entropy.mean": { "value": 1.3984159231185913, "min": 1.3984159231185913, "max": 1.421595811843872, "count": 33 }, "Worm.Policy.Entropy.sum": { "value": 41952.4765625, "min": 41952.4765625, "max": 42647.875, "count": 33 }, "Worm.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 33 }, "Worm.Environment.EpisodeLength.sum": { "value": 29970.0, "min": 29970.0, "max": 29970.0, "count": 33 }, "Worm.Step.mean": { "value": 989000.0, "min": 29000.0, "max": 989000.0, "count": 33 }, "Worm.Step.sum": { "value": 989000.0, "min": 29000.0, "max": 989000.0, "count": 33 }, "Worm.Policy.ExtrinsicValueEstimate.mean": { "value": 4.645773410797119, "min": 0.03545805439352989, "max": 4.645773410797119, "count": 33 }, "Worm.Policy.ExtrinsicValueEstimate.sum": { "value": 139.37319946289062, "min": 1.063741683959961, "max": 139.37319946289062, "count": 33 }, "Worm.Environment.CumulativeReward.mean": { "value": 51.389706452687584, "min": 0.2699026806900899, "max": 51.389706452687584, "count": 33 }, "Worm.Environment.CumulativeReward.sum": { "value": 1541.6911935806274, "min": 8.097080420702696, "max": 1541.6911935806274, "count": 33 }, "Worm.Policy.ExtrinsicReward.mean": { "value": 51.389706452687584, "min": 0.2699026806900899, "max": 51.389706452687584, "count": 33 }, "Worm.Policy.ExtrinsicReward.sum": { "value": 1541.6911935806274, "min": 8.097080420702696, "max": 1541.6911935806274, "count": 33 }, "Worm.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Worm.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Worm.Losses.PolicyLoss.mean": { "value": 0.021461021263218884, "min": 0.011847945722798786, "max": 0.021461021263218884, "count": 32 }, "Worm.Losses.PolicyLoss.sum": { "value": 0.021461021263218884, "min": 0.011847945722798786, "max": 0.021461021263218884, "count": 32 }, "Worm.Losses.ValueLoss.mean": { "value": 0.3633682309162049, "min": 0.0009824149005691566, "max": 0.3633682309162049, "count": 32 }, "Worm.Losses.ValueLoss.sum": { "value": 0.3633682309162049, "min": 0.0009824149005691566, "max": 0.3633682309162049, "count": 32 }, "Worm.Policy.LearningRate.mean": { "value": 1.2000096000000011e-05, "min": 1.2000096000000011e-05, "max": 0.0002910000029999999, "count": 32 }, "Worm.Policy.LearningRate.sum": { "value": 1.2000096000000011e-05, "min": 1.2000096000000011e-05, "max": 0.0002910000029999999, "count": 32 }, "Worm.Policy.Epsilon.mean": { "value": 0.10400000000000001, "min": 0.10400000000000001, "max": 0.19699999999999998, "count": 32 }, "Worm.Policy.Epsilon.sum": { "value": 0.10400000000000001, "min": 0.10400000000000001, "max": 0.19699999999999998, "count": 32 }, "Worm.Policy.Beta.mean": { "value": 0.00020960000000000022, "min": 0.00020960000000000022, "max": 0.0048503, "count": 32 }, "Worm.Policy.Beta.sum": { "value": 0.00020960000000000022, "min": 0.00020960000000000022, "max": 0.0048503, "count": 32 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1674572117", "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/Worm.yaml --env=./training-envs-executables/linux/Worm/Worm --run-id=worm --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": "1674573286" }, "total": 1168.994698718, "count": 1, "self": 0.3742903980009942, "children": { "run_training.setup": { "total": 0.09828740899956756, "count": 1, "self": 0.09828740899956756 }, "TrainerController.start_learning": { "total": 1168.5221209109995, "count": 1, "self": 1.6942699210358114, "children": { "TrainerController._reset_env": { "total": 6.090433678999943, "count": 1, "self": 6.090433678999943 }, "TrainerController.advance": { "total": 1160.6336055969641, "count": 101000, "self": 1.8393798760271238, "children": { "env_step": { "total": 952.6649497720673, "count": 101000, "self": 828.3673183899209, "children": { "SubprocessEnvManager._take_step": { "total": 123.1608932410636, "count": 101000, "self": 8.079562542142412, "children": { "TorchPolicy.evaluate": { "total": 115.08133069892119, "count": 101000, "self": 29.3462266761544, "children": { "TorchPolicy.sample_actions": { "total": 85.73510402276679, "count": 101000, "self": 85.73510402276679 } } } } }, "workers": { "total": 1.1367381410827875, "count": 101000, "self": 0.0, "children": { "worker_root": { "total": 1164.7757426650996, "count": 101000, "is_parallel": true, "self": 446.45702335019905, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010410819995740894, "count": 1, "is_parallel": true, "self": 0.0004339540000728448, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006071279995012446, "count": 2, "is_parallel": true, "self": 0.0006071279995012446 } } }, "UnityEnvironment.step": { "total": 0.027423702999840316, "count": 1, "is_parallel": true, "self": 0.00020436200065887533, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003893670000252314, "count": 1, "is_parallel": true, "self": 0.0003893670000252314 }, "communicator.exchange": { "total": 0.026251483999658376, "count": 1, "is_parallel": true, "self": 0.026251483999658376 }, "steps_from_proto": { "total": 0.0005784899994978332, "count": 1, "is_parallel": true, "self": 0.00023532599971076706, "children": { "_process_rank_one_or_two_observation": { "total": 0.00034316399978706613, "count": 2, "is_parallel": true, "self": 0.00034316399978706613 } } } } } } }, "UnityEnvironment.step": { "total": 718.3187193149006, "count": 100999, "is_parallel": true, "self": 15.839357220722377, "children": { "UnityEnvironment._generate_step_input": { "total": 28.833279780057637, "count": 100999, "is_parallel": true, "self": 28.833279780057637 }, "communicator.exchange": { "total": 631.3782747669002, "count": 100999, "is_parallel": true, "self": 631.3782747669002 }, "steps_from_proto": { "total": 42.2678075472204, "count": 100999, "is_parallel": true, "self": 16.21633365683465, "children": { "_process_rank_one_or_two_observation": { "total": 26.05147389038575, "count": 201998, "is_parallel": true, "self": 26.05147389038575 } } } } } } } } } } }, "trainer_advance": { "total": 206.1292759488697, "count": 101000, "self": 2.1547748671155205, "children": { "process_trajectory": { "total": 55.47216268775264, "count": 101000, "self": 55.253516591753396, "children": { "RLTrainer._checkpoint": { "total": 0.21864609599924734, "count": 2, "self": 0.21864609599924734 } } }, "_update_policy": { "total": 148.50233839400153, "count": 33, "self": 123.9741459529896, "children": { "TorchPPOOptimizer.update": { "total": 24.528192441011925, "count": 1386, "self": 24.528192441011925 } } } } } } }, "trainer_threads": { "total": 8.21999492472969e-07, "count": 1, "self": 8.21999492472969e-07 }, "TrainerController._save_models": { "total": 0.10381089200018323, "count": 1, "self": 0.00195359500048653, "children": { "RLTrainer._checkpoint": { "total": 0.1018572969996967, "count": 1, "self": 0.1018572969996967 } } } } } } }