mahdisf's picture
First Push
6a3462a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.18613862991333,
"min": 1.180540680885315,
"max": 2.889934778213501,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 11377.44140625,
"min": 11377.44140625,
"max": 29719.865234375,
"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": 12.755396842956543,
"min": 0.013637186028063297,
"max": 12.755396842956543,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2614.8564453125,
"min": 2.6456141471862793,
"max": 2614.8564453125,
"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": 25.29090909090909,
"min": 2.7045454545454546,
"max": 25.931818181818183,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1391.0,
"min": 119.0,
"max": 1426.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.29090909090909,
"min": 2.7045454545454546,
"max": 25.931818181818183,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1391.0,
"min": 119.0,
"max": 1426.0,
"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
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0215328708194041,
"min": 0.01655911677516997,
"max": 0.02936543757872035,
"count": 47
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.0215328708194041,
"min": 0.01655911677516997,
"max": 0.02936543757872035,
"count": 47
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.27473052044709523,
"min": 0.11846761082609494,
"max": 0.3540204723676046,
"count": 47
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.27473052044709523,
"min": 0.11846761082609494,
"max": 0.3540204723676046,
"count": 47
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.2176982607999905e-06,
"min": 5.2176982607999905e-06,
"max": 0.00029345280218239997,
"count": 47
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.2176982607999905e-06,
"min": 5.2176982607999905e-06,
"max": 0.00029345280218239997,
"count": 47
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10173919999999997,
"min": 0.10173919999999997,
"max": 0.19781759999999993,
"count": 47
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10173919999999997,
"min": 0.10173919999999997,
"max": 0.19781759999999993,
"count": 47
},
"SnowballTarget.Policy.Beta.mean": {
"value": 9.678607999999983e-05,
"min": 9.678607999999983e-05,
"max": 0.004891098240000001,
"count": 47
},
"SnowballTarget.Policy.Beta.sum": {
"value": 9.678607999999983e-05,
"min": 9.678607999999983e-05,
"max": 0.004891098240000001,
"count": 47
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1753988390",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/envs/myenv/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --train",
"mlagents_version": "1.1.0",
"mlagents_envs_version": "1.1.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1753989422"
},
"total": 1032.043569382,
"count": 1,
"self": 0.48963090400138753,
"children": {
"run_training.setup": {
"total": 0.018886557998484932,
"count": 1,
"self": 0.018886557998484932
},
"TrainerController.start_learning": {
"total": 1031.5350519200001,
"count": 1,
"self": 0.8973890988927451,
"children": {
"TrainerController._reset_env": {
"total": 2.7377465480003593,
"count": 1,
"self": 2.7377465480003593
},
"TrainerController.advance": {
"total": 1027.7927743611071,
"count": 45464,
"self": 0.9064976881782059,
"children": {
"env_step": {
"total": 780.7666278640409,
"count": 45464,
"self": 579.6289877330782,
"children": {
"SubprocessEnvManager._take_step": {
"total": 200.6172108599967,
"count": 45464,
"self": 3.2871830021795176,
"children": {
"TorchPolicy.evaluate": {
"total": 197.33002785781719,
"count": 45464,
"self": 197.33002785781719
}
}
},
"workers": {
"total": 0.5204292709659057,
"count": 45464,
"self": 0.0,
"children": {
"worker_root": {
"total": 1028.148960666791,
"count": 45464,
"is_parallel": true,
"self": 519.1166341139178,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002101230998960091,
"count": 1,
"is_parallel": true,
"self": 0.0006652530028077308,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00143597799615236,
"count": 10,
"is_parallel": true,
"self": 0.00143597799615236
}
}
},
"UnityEnvironment.step": {
"total": 0.034988708999662776,
"count": 1,
"is_parallel": true,
"self": 0.000601400000959984,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005470649994094856,
"count": 1,
"is_parallel": true,
"self": 0.0005470649994094856
},
"communicator.exchange": {
"total": 0.03193730100065295,
"count": 1,
"is_parallel": true,
"self": 0.03193730100065295
},
"steps_from_proto": {
"total": 0.0019029429986403557,
"count": 1,
"is_parallel": true,
"self": 0.00037371200232882984,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015292309963115258,
"count": 10,
"is_parallel": true,
"self": 0.0015292309963115258
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 509.0323265528732,
"count": 45463,
"is_parallel": true,
"self": 24.480910645439508,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 13.734148306088173,
"count": 45463,
"is_parallel": true,
"self": 13.734148306088173
},
"communicator.exchange": {
"total": 390.7014119101277,
"count": 45463,
"is_parallel": true,
"self": 390.7014119101277
},
"steps_from_proto": {
"total": 80.1158556912178,
"count": 45463,
"is_parallel": true,
"self": 14.158489778550575,
"children": {
"_process_rank_one_or_two_observation": {
"total": 65.95736591266723,
"count": 454630,
"is_parallel": true,
"self": 65.95736591266723
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 246.1196488088881,
"count": 45464,
"self": 1.053242166792188,
"children": {
"process_trajectory": {
"total": 123.03951380310718,
"count": 45464,
"self": 122.88185607810556,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1576577250016271,
"count": 1,
"self": 0.1576577250016271
}
}
},
"_update_policy": {
"total": 122.02689283898872,
"count": 47,
"self": 93.30386958095733,
"children": {
"TorchPPOOptimizer.update": {
"total": 28.72302325803139,
"count": 1410,
"self": 28.72302325803139
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.070008673006669e-07,
"count": 1,
"self": 9.070008673006669e-07
},
"TrainerController._save_models": {
"total": 0.1071410049989936,
"count": 1,
"self": 0.0005880139997316292,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10655299099926197,
"count": 1,
"self": 0.10655299099926197
}
}
}
}
}
}
}