cthiriet's picture
First Push
0e6135c
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.9876135587692261,
"min": 0.9876135587692261,
"max": 1.4458221197128296,
"count": 2
},
"Pyramids.Policy.Entropy.sum": {
"value": 29581.001953125,
"min": 29581.001953125,
"max": 43860.4609375,
"count": 2
},
"Pyramids.Step.mean": {
"value": 59904.0,
"min": 29952.0,
"max": 59904.0,
"count": 2
},
"Pyramids.Step.sum": {
"value": 59904.0,
"min": 29952.0,
"max": 59904.0,
"count": 2
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.07820718735456467,
"min": -0.07820718735456467,
"max": 0.004724619444459677,
"count": 2
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -18.769725799560547,
"min": -18.769725799560547,
"max": 1.119734764099121,
"count": 2
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.27379608154296875,
"min": 0.27131640911102295,
"max": 0.27379608154296875,
"count": 2
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 65.7110595703125,
"min": 64.30198669433594,
"max": 65.7110595703125,
"count": 2
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07156728498774782,
"min": 0.07156728498774782,
"max": 0.07170257468401815,
"count": 2
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.5009709949142348,
"min": 0.5009709949142348,
"max": 0.501918022788127,
"count": 2
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0019260614644661383,
"min": 0.0019260614644661383,
"max": 0.004694926092234338,
"count": 2
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.013482430251262967,
"min": 0.013482430251262967,
"max": 0.03286448264564036,
"count": 2
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00029558765861363806,
"min": 0.00029558765861363806,
"max": 0.00029838354339596195,
"count": 2
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0020691136102954665,
"min": 0.0020691136102954665,
"max": 0.0020886848037717336,
"count": 2
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.19852921904761905,
"min": 0.19852921904761905,
"max": 0.19946118095238097,
"count": 2
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.3897045333333333,
"min": 1.3897045333333333,
"max": 1.3962282666666668,
"count": 2
},
"Pyramids.Policy.Beta.mean": {
"value": 0.009853068982857144,
"min": 0.009853068982857144,
"max": 0.009946171977142856,
"count": 2
},
"Pyramids.Policy.Beta.sum": {
"value": 0.06897148288,
"min": 0.06897148288,
"max": 0.06962320384,
"count": 2
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.17660532891750336,
"min": 0.17660532891750336,
"max": 0.4363160729408264,
"count": 2
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 1.2362372875213623,
"min": 1.2362372875213623,
"max": 3.0542125701904297,
"count": 2
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 999.0,
"min": 999.0,
"max": 999.0,
"count": 2
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31968.0,
"min": 15984.0,
"max": 31968.0,
"count": 2
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -1.0000000521540642,
"min": -1.0000000521540642,
"max": -1.0000000521540642,
"count": 2
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -32.000001668930054,
"min": -32.000001668930054,
"max": -16.000000834465027,
"count": 2
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -1.0000000521540642,
"min": -1.0000000521540642,
"max": -1.0000000521540642,
"count": 2
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -32.000001668930054,
"min": -32.000001668930054,
"max": -16.000000834465027,
"count": 2
},
"Pyramids.Policy.RndReward.mean": {
"value": 2.432742123492062,
"min": 2.432742123492062,
"max": 8.319670120254159,
"count": 2
},
"Pyramids.Policy.RndReward.sum": {
"value": 77.84774795174599,
"min": 77.84774795174599,
"max": 133.11472192406654,
"count": 2
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1679788031",
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1679788189"
},
"total": 158.32821923699976,
"count": 1,
"self": 0.43773762499949953,
"children": {
"run_training.setup": {
"total": 0.12128202099984264,
"count": 1,
"self": 0.12128202099984264
},
"TrainerController.start_learning": {
"total": 157.76919959100042,
"count": 1,
"self": 0.10320775999252874,
"children": {
"TrainerController._reset_env": {
"total": 5.993670914000177,
"count": 1,
"self": 5.993670914000177
},
"TrainerController.advance": {
"total": 151.3684700170079,
"count": 5070,
"self": 0.11447721199374428,
"children": {
"env_step": {
"total": 102.41760444301235,
"count": 5070,
"self": 93.41205126704335,
"children": {
"SubprocessEnvManager._take_step": {
"total": 8.938063115993373,
"count": 5070,
"self": 0.3840448859659773,
"children": {
"TorchPolicy.evaluate": {
"total": 8.554018230027395,
"count": 5070,
"self": 8.554018230027395
}
}
},
"workers": {
"total": 0.06749005997562563,
"count": 5069,
"self": 0.0,
"children": {
"worker_root": {
"total": 157.2671037339951,
"count": 5069,
"is_parallel": true,
"self": 73.21221849401991,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017906680000123743,
"count": 1,
"is_parallel": true,
"self": 0.0005256360000203131,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012650319999920612,
"count": 8,
"is_parallel": true,
"self": 0.0012650319999920612
}
}
},
"UnityEnvironment.step": {
"total": 0.047435902999950486,
"count": 1,
"is_parallel": true,
"self": 0.0005807200004710467,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004918699996778741,
"count": 1,
"is_parallel": true,
"self": 0.0004918699996778741
},
"communicator.exchange": {
"total": 0.04475290499976836,
"count": 1,
"is_parallel": true,
"self": 0.04475290499976836
},
"steps_from_proto": {
"total": 0.0016104080000332033,
"count": 1,
"is_parallel": true,
"self": 0.0003441340013523586,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012662739986808447,
"count": 8,
"is_parallel": true,
"self": 0.0012662739986808447
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 84.05488523997519,
"count": 5068,
"is_parallel": true,
"self": 2.4464266439963467,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.8339763930021036,
"count": 5068,
"is_parallel": true,
"self": 1.8339763930021036
},
"communicator.exchange": {
"total": 72.54149900198126,
"count": 5068,
"is_parallel": true,
"self": 72.54149900198126
},
"steps_from_proto": {
"total": 7.232983200995477,
"count": 5068,
"is_parallel": true,
"self": 1.5035520689871191,
"children": {
"_process_rank_one_or_two_observation": {
"total": 5.729431132008358,
"count": 40544,
"is_parallel": true,
"self": 5.729431132008358
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 48.8363883620018,
"count": 5069,
"self": 0.12837802498097517,
"children": {
"process_trajectory": {
"total": 9.927637970021351,
"count": 5069,
"self": 9.927637970021351
},
"_update_policy": {
"total": 38.78037236699947,
"count": 20,
"self": 24.28174198301349,
"children": {
"TorchPPOOptimizer.update": {
"total": 14.498630383985983,
"count": 1875,
"self": 14.498630383985983
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.8639998415892478e-06,
"count": 1,
"self": 1.8639998415892478e-06
},
"TrainerController._save_models": {
"total": 0.30384903599997415,
"count": 1,
"self": 0.0068999579998489935,
"children": {
"RLTrainer._checkpoint": {
"total": 0.29694907800012516,
"count": 1,
"self": 0.29694907800012516
}
}
}
}
}
}
}