Rolo's picture
First Push
5c8b581
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7189579010009766,
"min": 0.7076094746589661,
"max": 2.886545419692993,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6935.787109375,
"min": 6865.7734375,
"max": 29656.3671875,
"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": 13.551231384277344,
"min": 0.10208213329315186,
"max": 13.551231384277344,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2778.00244140625,
"min": 19.80393409729004,
"max": 2778.00244140625,
"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": 26.30909090909091,
"min": 2.727272727272727,
"max": 26.977777777777778,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1447.0,
"min": 120.0,
"max": 1460.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.30909090909091,
"min": 2.727272727272727,
"max": 26.977777777777778,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1447.0,
"min": 120.0,
"max": 1460.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.03827309685242225,
"min": 0.03827309685242225,
"max": 0.056972225967055076,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.0765461937048445,
"min": 0.0765461937048445,
"max": 0.15979163250520678,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1827632489742017,
"min": 0.09480254347527436,
"max": 0.3014485729870453,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.3655264979484034,
"min": 0.18960508695054873,
"max": 0.9043457189611359,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.0528989824000053e-06,
"min": 3.0528989824000053e-06,
"max": 0.00029609280130239995,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 6.105797964800011e-06,
"min": 6.105797964800011e-06,
"max": 0.0008367984210671999,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10101760000000001,
"min": 0.10101760000000001,
"max": 0.1986976,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.20203520000000003,
"min": 0.20203520000000003,
"max": 0.5789328,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 4.042624000000006e-05,
"min": 4.042624000000006e-05,
"max": 0.00296105824,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 8.085248000000012e-05,
"min": 8.085248000000012e-05,
"max": 0.008370090719999999,
"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": "1675969766",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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=SnowballTarget2 --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1675970884"
},
"total": 1118.2555264050002,
"count": 1,
"self": 0.7368682540000009,
"children": {
"run_training.setup": {
"total": 0.11303626300002634,
"count": 1,
"self": 0.11303626300002634
},
"TrainerController.start_learning": {
"total": 1117.405621888,
"count": 1,
"self": 1.3353801209966605,
"children": {
"TrainerController._reset_env": {
"total": 9.897179979000043,
"count": 1,
"self": 9.897179979000043
},
"TrainerController.advance": {
"total": 1105.9662898170031,
"count": 45495,
"self": 0.6344023770077456,
"children": {
"env_step": {
"total": 1105.3318874399954,
"count": 45495,
"self": 775.3201560819981,
"children": {
"SubprocessEnvManager._take_step": {
"total": 329.34455177198197,
"count": 45495,
"self": 3.687963535001586,
"children": {
"TorchPolicy.evaluate": {
"total": 325.6565882369804,
"count": 45495,
"self": 68.72317378099808,
"children": {
"TorchPolicy.sample_actions": {
"total": 256.9334144559823,
"count": 45495,
"self": 256.9334144559823
}
}
}
}
},
"workers": {
"total": 0.6671795860153225,
"count": 45495,
"self": 0.0,
"children": {
"worker_root": {
"total": 1113.585899626991,
"count": 45495,
"is_parallel": true,
"self": 522.3459620519734,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006647186999998667,
"count": 1,
"is_parallel": true,
"self": 0.004133838000143442,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002513348999855225,
"count": 10,
"is_parallel": true,
"self": 0.002513348999855225
}
}
},
"UnityEnvironment.step": {
"total": 0.035653033000016876,
"count": 1,
"is_parallel": true,
"self": 0.0004838219998646309,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037226200004170096,
"count": 1,
"is_parallel": true,
"self": 0.00037226200004170096
},
"communicator.exchange": {
"total": 0.03298592800001643,
"count": 1,
"is_parallel": true,
"self": 0.03298592800001643
},
"steps_from_proto": {
"total": 0.0018110210000941152,
"count": 1,
"is_parallel": true,
"self": 0.00044708600012199895,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013639349999721162,
"count": 10,
"is_parallel": true,
"self": 0.0013639349999721162
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 591.2399375750176,
"count": 45494,
"is_parallel": true,
"self": 23.182700752049072,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 12.76913887200817,
"count": 45494,
"is_parallel": true,
"self": 12.76913887200817
},
"communicator.exchange": {
"total": 469.72578152598055,
"count": 45494,
"is_parallel": true,
"self": 469.72578152598055
},
"steps_from_proto": {
"total": 85.56231642497983,
"count": 45494,
"is_parallel": true,
"self": 17.292103979966214,
"children": {
"_process_rank_one_or_two_observation": {
"total": 68.27021244501361,
"count": 454940,
"is_parallel": true,
"self": 68.27021244501361
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012434900008884142,
"count": 1,
"self": 0.00012434900008884142,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1095.536035761749,
"count": 1265559,
"is_parallel": true,
"self": 31.090018209572463,
"children": {
"process_trajectory": {
"total": 772.4715815891767,
"count": 1265559,
"is_parallel": true,
"self": 769.5924127911774,
"children": {
"RLTrainer._checkpoint": {
"total": 2.8791687979993412,
"count": 10,
"is_parallel": true,
"self": 2.8791687979993412
}
}
},
"_update_policy": {
"total": 291.9744359629998,
"count": 113,
"is_parallel": true,
"self": 143.95654618600975,
"children": {
"TorchPPOOptimizer.update": {
"total": 148.01788977699005,
"count": 5760,
"is_parallel": true,
"self": 148.01788977699005
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.20664762199999132,
"count": 1,
"self": 0.001383956000154285,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20526366599983703,
"count": 1,
"self": 0.20526366599983703
}
}
}
}
}
}
}