dar-tau's picture
First Push
2706718
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.998111367225647,
"min": 1.9966723918914795,
"max": 2.88897442817688,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 19077.966796875,
"min": 19077.966796875,
"max": 29585.986328125,
"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": 6.432192802429199,
"min": 0.045326344668865204,
"max": 6.432192802429199,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1254.277587890625,
"min": 8.79331111907959,
"max": 1265.2921142578125,
"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.Environment.CumulativeReward.mean": {
"value": 15.795454545454545,
"min": 2.75,
"max": 16.236363636363638,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 695.0,
"min": 121.0,
"max": 893.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 15.795454545454545,
"min": 2.75,
"max": 16.236363636363638,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 695.0,
"min": 121.0,
"max": 893.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.035800327729551405,
"min": 0.031220143997264433,
"max": 0.04072730547940249,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.035800327729551405,
"min": 0.03155770312749904,
"max": 0.07076607536588449,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.30898376430074376,
"min": 0.08326070398713152,
"max": 0.30898376430074376,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.30898376430074376,
"min": 0.08326070398713152,
"max": 0.6064463830461688,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.9000987000000035e-06,
"min": 3.9000987000000035e-06,
"max": 0.00028770000409999996,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.9000987000000035e-06,
"min": 3.9000987000000035e-06,
"max": 0.000436032054656,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10129999999999999,
"min": 0.10129999999999999,
"max": 0.1959,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10129999999999999,
"min": 0.10129999999999999,
"max": 0.345344,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 7.487000000000006e-05,
"min": 7.487000000000006e-05,
"max": 0.00479541,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 7.487000000000006e-05,
"min": 7.487000000000006e-05,
"max": 0.0072726656,
"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": "1688146043",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "0.31.0.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": "1688146514"
},
"total": 471.8054127439999,
"count": 1,
"self": 0.43341298899986214,
"children": {
"run_training.setup": {
"total": 0.042734719000009136,
"count": 1,
"self": 0.042734719000009136
},
"TrainerController.start_learning": {
"total": 471.32926503600004,
"count": 1,
"self": 0.5444179199984092,
"children": {
"TrainerController._reset_env": {
"total": 4.437831095999968,
"count": 1,
"self": 4.437831095999968
},
"TrainerController.advance": {
"total": 466.1978835280016,
"count": 18200,
"self": 0.27170770601287586,
"children": {
"env_step": {
"total": 465.92617582198875,
"count": 18200,
"self": 334.9083867449756,
"children": {
"SubprocessEnvManager._take_step": {
"total": 130.74304560800294,
"count": 18200,
"self": 1.8240574260089488,
"children": {
"TorchPolicy.evaluate": {
"total": 128.918988181994,
"count": 18200,
"self": 128.918988181994
}
}
},
"workers": {
"total": 0.2747434690102182,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 469.7449597550011,
"count": 18200,
"is_parallel": true,
"self": 213.9690922929924,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005347698000036871,
"count": 1,
"is_parallel": true,
"self": 0.003756865999889669,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001590832000147202,
"count": 10,
"is_parallel": true,
"self": 0.001590832000147202
}
}
},
"UnityEnvironment.step": {
"total": 0.10656255100002454,
"count": 1,
"is_parallel": true,
"self": 0.0007871730000488242,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004906679999976404,
"count": 1,
"is_parallel": true,
"self": 0.0004906679999976404
},
"communicator.exchange": {
"total": 0.10295429200004946,
"count": 1,
"is_parallel": true,
"self": 0.10295429200004946
},
"steps_from_proto": {
"total": 0.0023304179999286134,
"count": 1,
"is_parallel": true,
"self": 0.0003944529997852442,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019359650001433693,
"count": 10,
"is_parallel": true,
"self": 0.0019359650001433693
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 255.7758674620087,
"count": 18199,
"is_parallel": true,
"self": 10.865352272050018,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.547644042982483,
"count": 18199,
"is_parallel": true,
"self": 5.547644042982483
},
"communicator.exchange": {
"total": 201.80336151396784,
"count": 18199,
"is_parallel": true,
"self": 201.80336151396784
},
"steps_from_proto": {
"total": 37.55950963300836,
"count": 18199,
"is_parallel": true,
"self": 6.871111281015828,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.688398351992532,
"count": 181990,
"is_parallel": true,
"self": 30.688398351992532
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.193200008259737e-05,
"count": 1,
"self": 7.193200008259737e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 460.528527923091,
"count": 642211,
"is_parallel": true,
"self": 14.683557747001942,
"children": {
"process_trajectory": {
"total": 341.64378137508913,
"count": 642211,
"is_parallel": true,
"self": 340.47655152408936,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1672298509997745,
"count": 4,
"is_parallel": true,
"self": 1.1672298509997745
}
}
},
"_update_policy": {
"total": 104.20118880099994,
"count": 23,
"is_parallel": true,
"self": 66.4194147179984,
"children": {
"TorchPPOOptimizer.update": {
"total": 37.78177408300155,
"count": 1137,
"is_parallel": true,
"self": 37.78177408300155
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1490605599999526,
"count": 1,
"self": 0.0008429949998571828,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14821756500009542,
"count": 1,
"self": 0.14821756500009542
}
}
}
}
}
}
}