MarBar's picture
First commit
75cf215
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8157879710197449,
"min": 0.8087843656539917,
"max": 2.840205669403076,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7887.85400390625,
"min": 7787.9775390625,
"max": 29149.03125,
"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": 27.637548446655273,
"min": 0.42227697372436523,
"max": 27.637548446655273,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 5665.697265625,
"min": 81.9217300415039,
"max": 5665.697265625,
"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.Losses.PolicyLoss.mean": {
"value": 0.0702910694246598,
"min": 0.06302175904090879,
"max": 0.07635165094363722,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.351455347123299,
"min": 0.25490457834059593,
"max": 0.3817582547181861,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1539918812977917,
"min": 0.1167713994432501,
"max": 0.2753529014394564,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7699594064889586,
"min": 0.4670855977730004,
"max": 1.376764507197282,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.0528989824000028e-06,
"min": 3.0528989824000028e-06,
"max": 0.00029675280108239997,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.5264494912000015e-05,
"min": 1.5264494912000015e-05,
"max": 0.0014540640153119996,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10203519999999999,
"min": 0.10203519999999999,
"max": 0.29783519999999997,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.510176,
"min": 0.42398080000000005,
"max": 1.469376,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00011165824000000009,
"min": 0.00011165824000000009,
"max": 0.00989186824,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005582912000000004,
"min": 0.0005582912000000004,
"max": 0.048470331199999994,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.363636363636363,
"min": 4.0227272727272725,
"max": 27.636363636363637,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1505.0,
"min": 177.0,
"max": 1505.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.363636363636363,
"min": 4.0227272727272725,
"max": 27.636363636363637,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1505.0,
"min": 177.0,
"max": 1505.0,
"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": "1698791656",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=SnowballTarget --no-graphics --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1698792982"
},
"total": 1325.265882864,
"count": 1,
"self": 0.5275657769998361,
"children": {
"run_training.setup": {
"total": 0.048488024000107544,
"count": 1,
"self": 0.048488024000107544
},
"TrainerController.start_learning": {
"total": 1324.6898290630002,
"count": 1,
"self": 1.7019708869820533,
"children": {
"TrainerController._reset_env": {
"total": 4.173030115999609,
"count": 1,
"self": 4.173030115999609
},
"TrainerController.advance": {
"total": 1318.719794959019,
"count": 45475,
"self": 0.8616533040240029,
"children": {
"env_step": {
"total": 1317.858141654995,
"count": 45475,
"self": 934.242048797023,
"children": {
"SubprocessEnvManager._take_step": {
"total": 382.78184691001843,
"count": 45475,
"self": 3.989752220010814,
"children": {
"TorchPolicy.evaluate": {
"total": 378.7920946900076,
"count": 45475,
"self": 378.7920946900076
}
}
},
"workers": {
"total": 0.8342459479536046,
"count": 45475,
"self": 0.0,
"children": {
"worker_root": {
"total": 1321.0429991109954,
"count": 45475,
"is_parallel": true,
"self": 664.6533978069301,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022121739998510748,
"count": 1,
"is_parallel": true,
"self": 0.0006726740002704901,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015394999995805847,
"count": 10,
"is_parallel": true,
"self": 0.0015394999995805847
}
}
},
"UnityEnvironment.step": {
"total": 0.046448951000002126,
"count": 1,
"is_parallel": true,
"self": 0.000710030999925948,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042752099989229464,
"count": 1,
"is_parallel": true,
"self": 0.00042752099989229464
},
"communicator.exchange": {
"total": 0.043205917999785015,
"count": 1,
"is_parallel": true,
"self": 0.043205917999785015
},
"steps_from_proto": {
"total": 0.0021054810003988678,
"count": 1,
"is_parallel": true,
"self": 0.00037916700057394337,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017263139998249244,
"count": 10,
"is_parallel": true,
"self": 0.0017263139998249244
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 656.3896013040653,
"count": 45474,
"is_parallel": true,
"self": 28.23255363290309,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 15.2268239840555,
"count": 45474,
"is_parallel": true,
"self": 15.2268239840555
},
"communicator.exchange": {
"total": 518.4403701270417,
"count": 45474,
"is_parallel": true,
"self": 518.4403701270417
},
"steps_from_proto": {
"total": 94.48985356006506,
"count": 45474,
"is_parallel": true,
"self": 18.647211631250684,
"children": {
"_process_rank_one_or_two_observation": {
"total": 75.84264192881437,
"count": 454740,
"is_parallel": true,
"self": 75.84264192881437
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.3664999793691095e-05,
"count": 1,
"self": 4.3664999793691095e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1308.2622780052761,
"count": 1267562,
"is_parallel": true,
"self": 28.278037944432526,
"children": {
"process_trajectory": {
"total": 697.6207581918411,
"count": 1267562,
"is_parallel": true,
"self": 696.1663667398407,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4543914520004364,
"count": 10,
"is_parallel": true,
"self": 1.4543914520004364
}
}
},
"_update_policy": {
"total": 582.3634818690025,
"count": 227,
"is_parallel": true,
"self": 187.00533453705793,
"children": {
"TorchPPOOptimizer.update": {
"total": 395.35814733194456,
"count": 15432,
"is_parallel": true,
"self": 395.35814733194456
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0949894359996506,
"count": 1,
"self": 0.0012213309996695898,
"children": {
"RLTrainer._checkpoint": {
"total": 0.093768104999981,
"count": 1,
"self": 0.093768104999981
}
}
}
}
}
}
}