BrennanDrake's picture
First Push
6c34d83 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9738112092018127,
"min": 0.9738112092018127,
"max": 2.8696212768554688,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9255.1015625,
"min": 9255.1015625,
"max": 29293.09375,
"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": 12.53433895111084,
"min": 0.013417893089354038,
"max": 12.53433895111084,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2444.196044921875,
"min": 2.6030712127685547,
"max": 2515.6904296875,
"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": 25.25,
"min": 2.9545454545454546,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1111.0,
"min": 130.0,
"max": 1395.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.25,
"min": 2.9545454545454546,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1111.0,
"min": 130.0,
"max": 1395.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0734725393490675,
"min": 0.06659840380883657,
"max": 0.07821692560113055,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.146945078698135,
"min": 0.13319680761767314,
"max": 0.2183060181721564,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18839407244733736,
"min": 0.10131306518300863,
"max": 0.3207307361991577,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.3767881448946747,
"min": 0.20262613036601726,
"max": 0.9621922085974731,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 6.432097856000005e-06,
"min": 6.432097856000005e-06,
"max": 0.000290232003256,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.286419571200001e-05,
"min": 1.286419571200001e-05,
"max": 0.0007419960526679999,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.103216,
"min": 0.103216,
"max": 0.24511600000000008,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.206432,
"min": 0.206432,
"max": 0.670998,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 7.410560000000005e-05,
"min": 7.410560000000005e-05,
"max": 0.0029026456000000003,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0001482112000000001,
"min": 0.0001482112000000001,
"max": 0.0074252268,
"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": "1768029760",
"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=SnowballTarget6 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1768030753"
},
"total": 993.299126932,
"count": 1,
"self": 0.8357426329994269,
"children": {
"run_training.setup": {
"total": 0.05389008200017997,
"count": 1,
"self": 0.05389008200017997
},
"TrainerController.start_learning": {
"total": 992.4094942170004,
"count": 1,
"self": 0.9621120410483854,
"children": {
"TrainerController._reset_env": {
"total": 3.019156219999786,
"count": 1,
"self": 3.019156219999786
},
"TrainerController.advance": {
"total": 988.3048698709526,
"count": 18192,
"self": 0.8700905949599473,
"children": {
"env_step": {
"total": 717.212013397012,
"count": 18192,
"self": 636.3243613520299,
"children": {
"SubprocessEnvManager._take_step": {
"total": 80.34957291196952,
"count": 18192,
"self": 3.2642052709989002,
"children": {
"TorchPolicy.evaluate": {
"total": 77.08536764097062,
"count": 18192,
"self": 77.08536764097062
}
}
},
"workers": {
"total": 0.5380791330126158,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 979.7391661569709,
"count": 18192,
"is_parallel": true,
"self": 435.1826247278859,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0034411100004945183,
"count": 1,
"is_parallel": true,
"self": 0.0008912470011637197,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0025498629993307986,
"count": 10,
"is_parallel": true,
"self": 0.0025498629993307986
}
}
},
"UnityEnvironment.step": {
"total": 0.08877080000002024,
"count": 1,
"is_parallel": true,
"self": 0.0007590880004499923,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004181479998806026,
"count": 1,
"is_parallel": true,
"self": 0.0004181479998806026
},
"communicator.exchange": {
"total": 0.08010843800002476,
"count": 1,
"is_parallel": true,
"self": 0.08010843800002476
},
"steps_from_proto": {
"total": 0.007485125999664888,
"count": 1,
"is_parallel": true,
"self": 0.002523980000660231,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004961145999004657,
"count": 10,
"is_parallel": true,
"self": 0.004961145999004657
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 544.556541429085,
"count": 18191,
"is_parallel": true,
"self": 17.066046039106368,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.257243749003464,
"count": 18191,
"is_parallel": true,
"self": 8.257243749003464
},
"communicator.exchange": {
"total": 429.60762100003467,
"count": 18191,
"is_parallel": true,
"self": 429.60762100003467
},
"steps_from_proto": {
"total": 89.62563064094047,
"count": 18191,
"is_parallel": true,
"self": 12.673414540828162,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.95221610011231,
"count": 181910,
"is_parallel": true,
"self": 76.95221610011231
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 270.2227658789807,
"count": 18192,
"self": 1.197827056922506,
"children": {
"process_trajectory": {
"total": 50.596090716057915,
"count": 18192,
"self": 49.9916339170577,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6044567990002179,
"count": 4,
"self": 0.6044567990002179
}
}
},
"_update_policy": {
"total": 218.42884810600026,
"count": 45,
"self": 90.79152720702314,
"children": {
"TorchPPOOptimizer.update": {
"total": 127.63732089897712,
"count": 4587,
"self": 127.63732089897712
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4469997040578164e-06,
"count": 1,
"self": 1.4469997040578164e-06
},
"TrainerController._save_models": {
"total": 0.12335463799990976,
"count": 1,
"self": 0.0019188089991075685,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12143582900080219,
"count": 1,
"self": 0.12143582900080219
}
}
}
}
}
}
}