HXW's picture
First Push
c32f110
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.97073894739151,
"min": 0.97073894739151,
"max": 2.855940580368042,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9268.615234375,
"min": 9268.615234375,
"max": 29247.6875,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.829907417297363,
"min": 0.4180363118648529,
"max": 12.829907417297363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2501.83203125,
"min": 81.09904479980469,
"max": 2579.72216796875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07015803256317489,
"min": 0.06319558100949507,
"max": 0.07691500784105088,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28063213025269956,
"min": 0.2527823240379803,
"max": 0.3845750392052544,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20235620475575036,
"min": 0.12664843872691706,
"max": 0.29780991907213245,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8094248190230015,
"min": 0.5065937549076682,
"max": 1.4890495953606622,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.5,
"min": 3.4318181818181817,
"max": 25.5,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1122.0,
"min": 151.0,
"max": 1395.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.5,
"min": 3.4318181818181817,
"max": 25.5,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1122.0,
"min": 151.0,
"max": 1395.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1678291398",
"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=SnowballTarget1 --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": "1.22.4",
"end_time_seconds": "1678291867"
},
"total": 468.20266338399995,
"count": 1,
"self": 0.39464307200000803,
"children": {
"run_training.setup": {
"total": 0.12561383000002024,
"count": 1,
"self": 0.12561383000002024
},
"TrainerController.start_learning": {
"total": 467.6824064819999,
"count": 1,
"self": 0.5385544629955348,
"children": {
"TrainerController._reset_env": {
"total": 9.274712148999924,
"count": 1,
"self": 9.274712148999924
},
"TrainerController.advance": {
"total": 457.74649452400433,
"count": 18203,
"self": 0.28714685999113954,
"children": {
"env_step": {
"total": 457.4593476640132,
"count": 18203,
"self": 314.48679740302623,
"children": {
"SubprocessEnvManager._take_step": {
"total": 142.70095715799573,
"count": 18203,
"self": 1.4971733289962685,
"children": {
"TorchPolicy.evaluate": {
"total": 141.20378382899946,
"count": 18203,
"self": 30.379106609003543,
"children": {
"TorchPolicy.sample_actions": {
"total": 110.82467721999592,
"count": 18203,
"self": 110.82467721999592
}
}
}
}
},
"workers": {
"total": 0.2715931029912326,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 466.1885932619949,
"count": 18203,
"is_parallel": true,
"self": 227.6643944069956,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005455514000004769,
"count": 1,
"is_parallel": true,
"self": 0.0035531109998601096,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001902403000144659,
"count": 10,
"is_parallel": true,
"self": 0.001902403000144659
}
}
},
"UnityEnvironment.step": {
"total": 0.05147178899994742,
"count": 1,
"is_parallel": true,
"self": 0.0005814139999529289,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004177619999836679,
"count": 1,
"is_parallel": true,
"self": 0.0004177619999836679
},
"communicator.exchange": {
"total": 0.0485928990000275,
"count": 1,
"is_parallel": true,
"self": 0.0485928990000275
},
"steps_from_proto": {
"total": 0.0018797139999833234,
"count": 1,
"is_parallel": true,
"self": 0.00043001599999570317,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014496979999876203,
"count": 10,
"is_parallel": true,
"self": 0.0014496979999876203
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 238.52419885499933,
"count": 18202,
"is_parallel": true,
"self": 9.595032033982534,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.270784792996551,
"count": 18202,
"is_parallel": true,
"self": 5.270784792996551
},
"communicator.exchange": {
"total": 192.65697600500107,
"count": 18202,
"is_parallel": true,
"self": 192.65697600500107
},
"steps_from_proto": {
"total": 31.00140602301917,
"count": 18202,
"is_parallel": true,
"self": 6.796087524010204,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.205318499008968,
"count": 182020,
"is_parallel": true,
"self": 24.205318499008968
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010060299996439426,
"count": 1,
"self": 0.00010060299996439426,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 454.28135395298875,
"count": 407340,
"is_parallel": true,
"self": 10.529600309982357,
"children": {
"process_trajectory": {
"total": 257.41911684000627,
"count": 407340,
"is_parallel": true,
"self": 256.3294411350063,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0896757049999906,
"count": 4,
"is_parallel": true,
"self": 1.0896757049999906
}
}
},
"_update_policy": {
"total": 186.33263680300013,
"count": 90,
"is_parallel": true,
"self": 67.32876850100286,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.00386830199727,
"count": 4587,
"is_parallel": true,
"self": 119.00386830199727
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12254474300016227,
"count": 1,
"self": 0.0011277310002242302,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12141701199993804,
"count": 1,
"self": 0.12141701199993804
}
}
}
}
}
}
}