ThePianist's picture
First training of SnowballTarget
faa055e
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9075040817260742,
"min": 0.9075040817260742,
"max": 2.856902599334717,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8694.796875,
"min": 8694.796875,
"max": 29320.390625,
"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": 13.512394905090332,
"min": 0.45154744386672974,
"max": 13.512394905090332,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2634.9169921875,
"min": 87.60020446777344,
"max": 2746.99365234375,
"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": 0.07388549774830822,
"min": 0.06571106797605085,
"max": 0.07388549774830822,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29554199099323286,
"min": 0.2628442719042034,
"max": 0.34756364058634703,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18698304858716094,
"min": 0.11659402846125885,
"max": 0.2538411946331753,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7479321943486438,
"min": 0.4663761138450354,
"max": 1.2692059731658765,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000007e-06,
"min": 8.082097306000007e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400003e-05,
"min": 3.232838922400003e-05,
"max": 0.0013851600382799997,
"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": 0.0001444306000000001,
"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": 26.727272727272727,
"min": 3.5454545454545454,
"max": 26.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1176.0,
"min": 156.0,
"max": 1457.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.727272727272727,
"min": 3.5454545454545454,
"max": 26.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1176.0,
"min": 156.0,
"max": 1457.0,
"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": "1679512412",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1679513108"
},
"total": 695.310977022,
"count": 1,
"self": 0.7824381760000279,
"children": {
"run_training.setup": {
"total": 0.10554839200000288,
"count": 1,
"self": 0.10554839200000288
},
"TrainerController.start_learning": {
"total": 694.422990454,
"count": 1,
"self": 0.6257942849971414,
"children": {
"TrainerController._reset_env": {
"total": 9.742794366999988,
"count": 1,
"self": 9.742794366999988
},
"TrainerController.advance": {
"total": 683.8210344650028,
"count": 18216,
"self": 0.33427227701065476,
"children": {
"env_step": {
"total": 683.4867621879921,
"count": 18216,
"self": 551.8728394459944,
"children": {
"SubprocessEnvManager._take_step": {
"total": 131.1361757360026,
"count": 18216,
"self": 1.8637340250050158,
"children": {
"TorchPolicy.evaluate": {
"total": 129.27244171099758,
"count": 18216,
"self": 129.27244171099758
}
}
},
"workers": {
"total": 0.4777470059951554,
"count": 18216,
"self": 0.0,
"children": {
"worker_root": {
"total": 692.5366698539945,
"count": 18216,
"is_parallel": true,
"self": 436.77697622699657,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005530832999994573,
"count": 1,
"is_parallel": true,
"self": 0.004108878999971921,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014219540000226516,
"count": 10,
"is_parallel": true,
"self": 0.0014219540000226516
}
}
},
"UnityEnvironment.step": {
"total": 0.10305963099997939,
"count": 1,
"is_parallel": true,
"self": 0.0005640220000202589,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003778359999841996,
"count": 1,
"is_parallel": true,
"self": 0.0003778359999841996
},
"communicator.exchange": {
"total": 0.10024136799998473,
"count": 1,
"is_parallel": true,
"self": 0.10024136799998473
},
"steps_from_proto": {
"total": 0.0018764049999902,
"count": 1,
"is_parallel": true,
"self": 0.0004175049999730618,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014589000000171382,
"count": 10,
"is_parallel": true,
"self": 0.0014589000000171382
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 255.75969362699786,
"count": 18215,
"is_parallel": true,
"self": 9.889929248995912,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.287382400003594,
"count": 18215,
"is_parallel": true,
"self": 5.287382400003594
},
"communicator.exchange": {
"total": 208.49978467499523,
"count": 18215,
"is_parallel": true,
"self": 208.49978467499523
},
"steps_from_proto": {
"total": 32.082597303003126,
"count": 18215,
"is_parallel": true,
"self": 6.608950775009447,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.47364652799368,
"count": 182150,
"is_parallel": true,
"self": 25.47364652799368
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001667600000700986,
"count": 1,
"self": 0.0001667600000700986,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 680.1858083479618,
"count": 451202,
"is_parallel": true,
"self": 10.83332877391399,
"children": {
"process_trajectory": {
"total": 263.9592667450481,
"count": 451202,
"is_parallel": true,
"self": 262.3141286720481,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6451380729999983,
"count": 4,
"is_parallel": true,
"self": 1.6451380729999983
}
}
},
"_update_policy": {
"total": 405.3932128289997,
"count": 90,
"is_parallel": true,
"self": 179.46547628499647,
"children": {
"TorchPPOOptimizer.update": {
"total": 225.92773654400324,
"count": 15290,
"is_parallel": true,
"self": 225.92773654400324
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.23320057700004782,
"count": 1,
"self": 0.0014479310000297119,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2317526460000181,
"count": 1,
"self": 0.2317526460000181
}
}
}
}
}
}
}