antonchirikalov's picture
First Push
6ec1f78 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9185342192649841,
"min": 0.8842411041259766,
"max": 2.853400707244873,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8810.580078125,
"min": 8481.640625,
"max": 29127.513671875,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.851017951965332,
"min": 0.4073438048362732,
"max": 13.899724006652832,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2839.458740234375,
"min": 79.02469635009766,
"max": 2849.443359375,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.049061481571698096,
"min": 0.03821129696831728,
"max": 0.05707437201829938,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24530740785849048,
"min": 0.1668860194258741,
"max": 0.2853718600914969,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1572996919353803,
"min": 0.13760178466327488,
"max": 0.33622988499701023,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7864984596769015,
"min": 0.5504071386530995,
"max": 1.463904950146874,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.0528989824000023e-06,
"min": 3.0528989824000023e-06,
"max": 0.00029675280108239997,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.526449491200001e-05,
"min": 1.526449491200001e-05,
"max": 0.001454064015312,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1010176,
"min": 0.1010176,
"max": 0.19891760000000003,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.505088,
"min": 0.41199040000000003,
"max": 0.984688,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00011165824000000006,
"min": 0.00011165824000000006,
"max": 0.00989186824,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005582912000000003,
"min": 0.0005582912000000003,
"max": 0.0484703312,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.345454545454544,
"min": 3.6136363636363638,
"max": 27.35185185185185,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1504.0,
"min": 159.0,
"max": 1504.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.345454545454544,
"min": 3.6136363636363638,
"max": 27.35185185185185,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1504.0,
"min": 159.0,
"max": 1504.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1754049815",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1754050782"
},
"total": 967.113669527,
"count": 1,
"self": 0.4409793739999941,
"children": {
"run_training.setup": {
"total": 0.0246975539999994,
"count": 1,
"self": 0.0246975539999994
},
"TrainerController.start_learning": {
"total": 966.647992599,
"count": 1,
"self": 0.8127938690072369,
"children": {
"TrainerController._reset_env": {
"total": 3.733117640000046,
"count": 1,
"self": 3.733117640000046
},
"TrainerController.advance": {
"total": 961.9664887939928,
"count": 45464,
"self": 0.8660069470306553,
"children": {
"env_step": {
"total": 727.3147498139981,
"count": 45464,
"self": 558.6392842880394,
"children": {
"SubprocessEnvManager._take_step": {
"total": 168.1883184489733,
"count": 45464,
"self": 2.992907177954976,
"children": {
"TorchPolicy.evaluate": {
"total": 165.19541127101832,
"count": 45464,
"self": 165.19541127101832
}
}
},
"workers": {
"total": 0.48714707698536586,
"count": 45464,
"self": 0.0,
"children": {
"worker_root": {
"total": 963.3944324989964,
"count": 45464,
"is_parallel": true,
"self": 473.4646638190019,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005210827999917456,
"count": 1,
"is_parallel": true,
"self": 0.003735380999842164,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014754470000752917,
"count": 10,
"is_parallel": true,
"self": 0.0014754470000752917
}
}
},
"UnityEnvironment.step": {
"total": 0.034607373999961055,
"count": 1,
"is_parallel": true,
"self": 0.0006052819999240455,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004202869999971881,
"count": 1,
"is_parallel": true,
"self": 0.0004202869999971881
},
"communicator.exchange": {
"total": 0.03164988700007143,
"count": 1,
"is_parallel": true,
"self": 0.03164988700007143
},
"steps_from_proto": {
"total": 0.001931917999968391,
"count": 1,
"is_parallel": true,
"self": 0.00044062300003133714,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001491294999937054,
"count": 10,
"is_parallel": true,
"self": 0.001491294999937054
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 489.9297686799945,
"count": 45463,
"is_parallel": true,
"self": 23.81427175697911,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 12.945854496015727,
"count": 45463,
"is_parallel": true,
"self": 12.945854496015727
},
"communicator.exchange": {
"total": 378.083549477989,
"count": 45463,
"is_parallel": true,
"self": 378.083549477989
},
"steps_from_proto": {
"total": 75.08609294901066,
"count": 45463,
"is_parallel": true,
"self": 13.286087670950337,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.800005278060326,
"count": 454630,
"is_parallel": true,
"self": 61.800005278060326
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 233.785732032964,
"count": 45464,
"self": 1.004273915957242,
"children": {
"process_trajectory": {
"total": 66.92079334500454,
"count": 45464,
"self": 65.28213018500446,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6386631600000783,
"count": 10,
"self": 1.6386631600000783
}
}
},
"_update_policy": {
"total": 165.86066477200222,
"count": 227,
"self": 91.8848622770006,
"children": {
"TorchPPOOptimizer.update": {
"total": 73.97580249500163,
"count": 5448,
"self": 73.97580249500163
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.220000265486306e-07,
"count": 1,
"self": 9.220000265486306e-07
},
"TrainerController._save_models": {
"total": 0.13559137399988686,
"count": 1,
"self": 0.0018436279999605176,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13374774599992634,
"count": 1,
"self": 0.13374774599992634
}
}
}
}
}
}
}