bk6000's picture
First Push
e598120
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.171149253845215,
"min": 2.171149253845215,
"max": 2.8903443813323975,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 20873.4296875,
"min": 20873.4296875,
"max": 29663.603515625,
"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": 5.1989521980285645,
"min": -0.10963883250951767,
"max": 5.1989521980285645,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1013.795654296875,
"min": -21.269933700561523,
"max": 1017.579345703125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 14.0,
"min": 2.659090909090909,
"max": 14.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 616.0,
"min": 117.0,
"max": 764.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 14.0,
"min": 2.659090909090909,
"max": 14.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 616.0,
"min": 117.0,
"max": 764.0,
"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
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.028098968579433857,
"min": 0.028098968579433857,
"max": 0.04366616293167074,
"count": 19
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.028098968579433857,
"min": 0.028098968579433857,
"max": 0.04366616293167074,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.3395604476332664,
"min": 0.08532781668362163,
"max": 0.3395604476332664,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.3395604476332664,
"min": 0.08532781668362163,
"max": 0.3395604476332664,
"count": 19
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.944099352000012e-06,
"min": 1.944099352000012e-06,
"max": 0.0002836320054559999,
"count": 19
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.944099352000012e-06,
"min": 1.944099352000012e-06,
"max": 0.0002836320054559999,
"count": 19
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10064800000000002,
"min": 0.10064800000000002,
"max": 0.19454400000000008,
"count": 19
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10064800000000002,
"min": 0.10064800000000002,
"max": 0.19454400000000008,
"count": 19
},
"SnowballTarget.Policy.Beta.mean": {
"value": 4.233520000000021e-05,
"min": 4.233520000000021e-05,
"max": 0.0047277456,
"count": 19
},
"SnowballTarget.Policy.Beta.sum": {
"value": 4.233520000000021e-05,
"min": 4.233520000000021e-05,
"max": 0.0047277456,
"count": 19
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1690400183",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"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": "0.31.0.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": "1690400629"
},
"total": 446.2850538360001,
"count": 1,
"self": 0.8036862030000975,
"children": {
"run_training.setup": {
"total": 0.05110250400002769,
"count": 1,
"self": 0.05110250400002769
},
"TrainerController.start_learning": {
"total": 445.43026512899996,
"count": 1,
"self": 0.5562650020096953,
"children": {
"TrainerController._reset_env": {
"total": 6.070799304000047,
"count": 1,
"self": 6.070799304000047
},
"TrainerController.advance": {
"total": 438.5903524239902,
"count": 18224,
"self": 0.24976553098554177,
"children": {
"env_step": {
"total": 438.3405868930047,
"count": 18224,
"self": 318.20462011600125,
"children": {
"SubprocessEnvManager._take_step": {
"total": 119.86178059800568,
"count": 18224,
"self": 2.0993753789939547,
"children": {
"TorchPolicy.evaluate": {
"total": 117.76240521901173,
"count": 18224,
"self": 117.76240521901173
}
}
},
"workers": {
"total": 0.274186178997752,
"count": 18224,
"self": 0.0,
"children": {
"worker_root": {
"total": 443.7066732030057,
"count": 18224,
"is_parallel": true,
"self": 203.59900529000993,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0068037389999062725,
"count": 1,
"is_parallel": true,
"self": 0.004447453000011592,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023562859998946806,
"count": 10,
"is_parallel": true,
"self": 0.0023562859998946806
}
}
},
"UnityEnvironment.step": {
"total": 0.04067337400010729,
"count": 1,
"is_parallel": true,
"self": 0.0006296340002336365,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004062900000008085,
"count": 1,
"is_parallel": true,
"self": 0.0004062900000008085
},
"communicator.exchange": {
"total": 0.03738385199994809,
"count": 1,
"is_parallel": true,
"self": 0.03738385199994809
},
"steps_from_proto": {
"total": 0.00225359799992475,
"count": 1,
"is_parallel": true,
"self": 0.00038784399976066197,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018657540001640882,
"count": 10,
"is_parallel": true,
"self": 0.0018657540001640882
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 240.1076679129958,
"count": 18223,
"is_parallel": true,
"self": 10.582294676997435,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.263294899992616,
"count": 18223,
"is_parallel": true,
"self": 5.263294899992616
},
"communicator.exchange": {
"total": 189.46666194799604,
"count": 18223,
"is_parallel": true,
"self": 189.46666194799604
},
"steps_from_proto": {
"total": 34.7954163880097,
"count": 18223,
"is_parallel": true,
"self": 6.514468051998165,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.280948336011534,
"count": 182230,
"is_parallel": true,
"self": 28.280948336011534
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.16120000056253e-05,
"count": 1,
"self": 9.16120000056253e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 433.3917632029179,
"count": 597111,
"is_parallel": true,
"self": 13.74705007695411,
"children": {
"process_trajectory": {
"total": 326.4674596539637,
"count": 597111,
"is_parallel": true,
"self": 325.33750530496377,
"children": {
"RLTrainer._checkpoint": {
"total": 1.129954348999945,
"count": 4,
"is_parallel": true,
"self": 1.129954348999945
}
}
},
"_update_policy": {
"total": 93.17725347200007,
"count": 19,
"is_parallel": true,
"self": 61.298014550005746,
"children": {
"TorchPPOOptimizer.update": {
"total": 31.87923892199433,
"count": 1155,
"is_parallel": true,
"self": 31.87923892199433
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.21275678699998934,
"count": 1,
"self": 0.0007777929999974731,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21197899399999187,
"count": 1,
"self": 0.21197899399999187
}
}
}
}
}
}
}