juanzinser's picture
First Push
c27a117 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.97171550989151,
"min": 0.9690284132957458,
"max": 2.856203317642212,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9277.939453125,
"min": 9277.939453125,
"max": 29250.37890625,
"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": 12.70871353149414,
"min": 0.21570941805839539,
"max": 12.70871353149414,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2478.19921875,
"min": 41.847625732421875,
"max": 2570.6962890625,
"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.Losses.PolicyLoss.mean": {
"value": 0.06646024838975043,
"min": 0.06219149055558613,
"max": 0.08059046144355271,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2658409935590017,
"min": 0.2487659622223445,
"max": 0.36757761771806663,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19913806342611126,
"min": 0.11063407487624013,
"max": 0.3017255678480747,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.796552253704445,
"min": 0.44253629950496054,
"max": 1.4324023118790459,
"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": 25.045454545454547,
"min": 3.0454545454545454,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1102.0,
"min": 134.0,
"max": 1383.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.045454545454547,
"min": 3.0454545454545454,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1102.0,
"min": 134.0,
"max": 1383.0,
"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": "1717182577",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1717183047"
},
"total": 469.8847388429999,
"count": 1,
"self": 0.48254554800018923,
"children": {
"run_training.setup": {
"total": 0.06166290499982097,
"count": 1,
"self": 0.06166290499982097
},
"TrainerController.start_learning": {
"total": 469.3405303899999,
"count": 1,
"self": 0.6233666240029834,
"children": {
"TrainerController._reset_env": {
"total": 3.7901375220001228,
"count": 1,
"self": 3.7901375220001228
},
"TrainerController.advance": {
"total": 464.83307983099667,
"count": 18201,
"self": 0.28770124800234953,
"children": {
"env_step": {
"total": 464.5453785829943,
"count": 18201,
"self": 302.50693133300274,
"children": {
"SubprocessEnvManager._take_step": {
"total": 161.7319285149954,
"count": 18201,
"self": 1.5377507140181024,
"children": {
"TorchPolicy.evaluate": {
"total": 160.1941778009773,
"count": 18201,
"self": 160.1941778009773
}
}
},
"workers": {
"total": 0.30651873499618887,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 468.0533505549872,
"count": 18201,
"is_parallel": true,
"self": 236.550305954976,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005353921000050832,
"count": 1,
"is_parallel": true,
"self": 0.0037828190002073825,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015711019998434494,
"count": 10,
"is_parallel": true,
"self": 0.0015711019998434494
}
}
},
"UnityEnvironment.step": {
"total": 0.08982371699994474,
"count": 1,
"is_parallel": true,
"self": 0.0006745250000221858,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003897399999459594,
"count": 1,
"is_parallel": true,
"self": 0.0003897399999459594
},
"communicator.exchange": {
"total": 0.08692633999999089,
"count": 1,
"is_parallel": true,
"self": 0.08692633999999089
},
"steps_from_proto": {
"total": 0.0018331119999857037,
"count": 1,
"is_parallel": true,
"self": 0.000359183999535162,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014739280004505417,
"count": 10,
"is_parallel": true,
"self": 0.0014739280004505417
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 231.5030446000112,
"count": 18200,
"is_parallel": true,
"self": 10.48642302704252,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.664413534011146,
"count": 18200,
"is_parallel": true,
"self": 5.664413534011146
},
"communicator.exchange": {
"total": 180.46261655999,
"count": 18200,
"is_parallel": true,
"self": 180.46261655999
},
"steps_from_proto": {
"total": 34.88959147896753,
"count": 18200,
"is_parallel": true,
"self": 6.591127790934252,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.29846368803328,
"count": 182000,
"is_parallel": true,
"self": 28.29846368803328
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014729500003340945,
"count": 1,
"self": 0.00014729500003340945,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 459.19533737998427,
"count": 689274,
"is_parallel": true,
"self": 14.587331009850232,
"children": {
"process_trajectory": {
"total": 254.26416400213384,
"count": 689274,
"is_parallel": true,
"self": 253.50546488313375,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7586991190000845,
"count": 4,
"is_parallel": true,
"self": 0.7586991190000845
}
}
},
"_update_policy": {
"total": 190.3438423680002,
"count": 90,
"is_parallel": true,
"self": 61.082383469011575,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.26145889898862,
"count": 4587,
"is_parallel": true,
"self": 129.26145889898862
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09379911800010632,
"count": 1,
"self": 0.000902951000171015,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0928961669999353,
"count": 1,
"self": 0.0928961669999353
}
}
}
}
}
}
}