rosalinec's picture
First Push
f45c1b0 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.5547899007797241,
"min": 1.5547899007797241,
"max": 2.8843562602996826,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 14776.7236328125,
"min": 14776.7236328125,
"max": 29500.69140625,
"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": 7.507135391235352,
"min": 0.11681630462408066,
"max": 7.507135391235352,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1463.891357421875,
"min": 22.662363052368164,
"max": 1519.495361328125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.051292604652796094,
"min": 0.04245707173708979,
"max": 0.05539776787837809,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.20517041861118437,
"min": 0.16982828694835916,
"max": 0.27698883939189045,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.29976441323136294,
"min": 0.0900099507610624,
"max": 0.29976441323136294,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.1990576529254517,
"min": 0.3600398030442496,
"max": 1.4694643778105578,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.694097306000002e-06,
"min": 2.694097306000002e-06,
"max": 9.7294002706e-05,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.0776389224000008e-05,
"min": 1.0776389224000008e-05,
"max": 0.00046172003828,
"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": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014443060000000012,
"min": 0.00014443060000000012,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000005,
"min": 0.0005777224000000005,
"max": 0.023089828,
"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.Environment.CumulativeReward.mean": {
"value": 15.045454545454545,
"min": 2.5681818181818183,
"max": 15.236363636363636,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 662.0,
"min": 113.0,
"max": 838.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 15.045454545454545,
"min": 2.5681818181818183,
"max": 15.236363636363636,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 662.0,
"min": 113.0,
"max": 838.0,
"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": "1746419415",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1746419840"
},
"total": 425.55833201200005,
"count": 1,
"self": 0.3875420690001192,
"children": {
"run_training.setup": {
"total": 0.030041704999916874,
"count": 1,
"self": 0.030041704999916874
},
"TrainerController.start_learning": {
"total": 425.140748238,
"count": 1,
"self": 0.4148497360059764,
"children": {
"TrainerController._reset_env": {
"total": 3.121651356999905,
"count": 1,
"self": 3.121651356999905
},
"TrainerController.advance": {
"total": 421.519403050994,
"count": 18192,
"self": 0.4301265099934426,
"children": {
"env_step": {
"total": 324.34137934699504,
"count": 18192,
"self": 247.24334606698426,
"children": {
"SubprocessEnvManager._take_step": {
"total": 76.85869759699722,
"count": 18192,
"self": 1.3902382049982407,
"children": {
"TorchPolicy.evaluate": {
"total": 75.46845939199898,
"count": 18192,
"self": 75.46845939199898
}
}
},
"workers": {
"total": 0.23933568301356445,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 423.62126886499357,
"count": 18192,
"is_parallel": true,
"self": 207.60418340598608,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005724352000015642,
"count": 1,
"is_parallel": true,
"self": 0.004180039000175384,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015443129998402583,
"count": 10,
"is_parallel": true,
"self": 0.0015443129998402583
}
}
},
"UnityEnvironment.step": {
"total": 0.04019335099997079,
"count": 1,
"is_parallel": true,
"self": 0.0006360849997690821,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039060700009940774,
"count": 1,
"is_parallel": true,
"self": 0.00039060700009940774
},
"communicator.exchange": {
"total": 0.037148996000041734,
"count": 1,
"is_parallel": true,
"self": 0.037148996000041734
},
"steps_from_proto": {
"total": 0.0020176630000605655,
"count": 1,
"is_parallel": true,
"self": 0.00039445599998089165,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016232070000796739,
"count": 10,
"is_parallel": true,
"self": 0.0016232070000796739
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 216.0170854590075,
"count": 18191,
"is_parallel": true,
"self": 10.22445504599932,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.876757482003541,
"count": 18191,
"is_parallel": true,
"self": 5.876757482003541
},
"communicator.exchange": {
"total": 165.6634052439979,
"count": 18191,
"is_parallel": true,
"self": 165.6634052439979
},
"steps_from_proto": {
"total": 34.25246768700674,
"count": 18191,
"is_parallel": true,
"self": 6.413101124025502,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.83936656298124,
"count": 181910,
"is_parallel": true,
"self": 27.83936656298124
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 96.74789719400553,
"count": 18192,
"self": 0.5205678960082878,
"children": {
"process_trajectory": {
"total": 28.414852557996824,
"count": 18192,
"self": 27.965340082997045,
"children": {
"RLTrainer._checkpoint": {
"total": 0.44951247499977853,
"count": 4,
"self": 0.44951247499977853
}
}
},
"_update_policy": {
"total": 67.81247674000042,
"count": 90,
"self": 38.38292657200202,
"children": {
"TorchPPOOptimizer.update": {
"total": 29.4295501679984,
"count": 2160,
"self": 29.4295501679984
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3860001217835816e-06,
"count": 1,
"self": 1.3860001217835816e-06
},
"TrainerController._save_models": {
"total": 0.08484270799999649,
"count": 1,
"self": 0.0008447360000900517,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08399797199990644,
"count": 1,
"self": 0.08399797199990644
}
}
}
}
}
}
}