IlluminatiPudding's picture
First Push
bda2108
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.888556957244873,
"min": 0.888556957244873,
"max": 2.871840715408325,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8532.8125,
"min": 8532.8125,
"max": 30107.91015625,
"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": 12.500067710876465,
"min": 0.25111350417137146,
"max": 12.500067710876465,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1262.5068359375,
"min": 24.358009338378906,
"max": 1262.5068359375,
"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.Environment.CumulativeReward.mean": {
"value": 24.73076923076923,
"min": 3.090909090909091,
"max": 24.78,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1286.0,
"min": 136.0,
"max": 1286.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.73076923076923,
"min": 3.090909090909091,
"max": 24.78,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1286.0,
"min": 136.0,
"max": 1286.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.04519401411797238,
"min": 0.03867056030770376,
"max": 0.05261207670458438,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.18077605647188952,
"min": 0.17242876052235565,
"max": 0.2630603835229219,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21814929678415257,
"min": 0.11759456351865083,
"max": 0.3107354794628918,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8725971871366103,
"min": 0.4703782540746033,
"max": 1.5170512329787016,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.950097350000006e-06,
"min": 7.950097350000006e-06,
"max": 0.00029175000274999995,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.1800389400000025e-05,
"min": 3.1800389400000025e-05,
"max": 0.0013845000385,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10265000000000002,
"min": 0.10265000000000002,
"max": 0.19725,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4106000000000001,
"min": 0.4106000000000001,
"max": 0.9615000000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014223500000000016,
"min": 0.00014223500000000016,
"max": 0.004862775,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005689400000000006,
"min": 0.0005689400000000006,
"max": 0.02307885,
"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": "1699449983",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.0.0",
"mlagents_envs_version": "1.0.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.21.2",
"end_time_seconds": "1699450463"
},
"total": 479.707697027,
"count": 1,
"self": 0.425346088999504,
"children": {
"run_training.setup": {
"total": 0.06556164300036471,
"count": 1,
"self": 0.06556164300036471
},
"TrainerController.start_learning": {
"total": 479.2167892950001,
"count": 1,
"self": 0.6532978539626129,
"children": {
"TrainerController._reset_env": {
"total": 8.615256814000531,
"count": 1,
"self": 8.615256814000531
},
"TrainerController.advance": {
"total": 469.85905003603784,
"count": 18207,
"self": 0.3023779990444382,
"children": {
"env_step": {
"total": 469.5566720369934,
"count": 18207,
"self": 303.9754270190433,
"children": {
"SubprocessEnvManager._take_step": {
"total": 165.26389112997003,
"count": 18207,
"self": 1.5523088698628271,
"children": {
"TorchPolicy.evaluate": {
"total": 163.7115822601072,
"count": 18207,
"self": 163.7115822601072
}
}
},
"workers": {
"total": 0.3173538879800617,
"count": 18207,
"self": 0.0,
"children": {
"worker_root": {
"total": 477.8290221639636,
"count": 18207,
"is_parallel": true,
"self": 222.48757326097075,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0031032939996293862,
"count": 1,
"is_parallel": true,
"self": 0.0008410400023421971,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002262253997287189,
"count": 10,
"is_parallel": true,
"self": 0.002262253997287189
}
}
},
"UnityEnvironment.step": {
"total": 0.05100161099926481,
"count": 1,
"is_parallel": true,
"self": 0.0006789339986426057,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004954369996994501,
"count": 1,
"is_parallel": true,
"self": 0.0004954369996994501
},
"communicator.exchange": {
"total": 0.04587444300068455,
"count": 1,
"is_parallel": true,
"self": 0.04587444300068455
},
"steps_from_proto": {
"total": 0.003952797000238206,
"count": 1,
"is_parallel": true,
"self": 0.0022496950014101458,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017031019988280605,
"count": 10,
"is_parallel": true,
"self": 0.0017031019988280605
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 255.34144890299285,
"count": 18206,
"is_parallel": true,
"self": 10.932669353005622,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.646420070000204,
"count": 18206,
"is_parallel": true,
"self": 5.646420070000204
},
"communicator.exchange": {
"total": 200.25166170599005,
"count": 18206,
"is_parallel": true,
"self": 200.25166170599005
},
"steps_from_proto": {
"total": 38.51069777399698,
"count": 18206,
"is_parallel": true,
"self": 7.328435596942654,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.182262177054326,
"count": 182060,
"is_parallel": true,
"self": 31.182262177054326
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00023997999960556626,
"count": 1,
"self": 0.00023997999960556626,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 465.71925331695184,
"count": 525503,
"is_parallel": true,
"self": 11.019622140963293,
"children": {
"process_trajectory": {
"total": 273.91614866299005,
"count": 525503,
"is_parallel": true,
"self": 270.3500793949888,
"children": {
"RLTrainer._checkpoint": {
"total": 3.566069268001229,
"count": 20,
"is_parallel": true,
"self": 3.566069268001229
}
}
},
"_update_policy": {
"total": 180.7834825129985,
"count": 90,
"is_parallel": true,
"self": 80.68942564901499,
"children": {
"TorchPPOOptimizer.update": {
"total": 100.0940568639835,
"count": 2160,
"is_parallel": true,
"self": 100.0940568639835
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08894461099953332,
"count": 1,
"self": 0.0010462589998496696,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08789835199968365,
"count": 1,
"self": 0.08789835199968365
}
}
}
}
}
}
}