SnowballTarget1 / run_logs /timers.json
Artachtron's picture
First training of SnowballTarget
5b94341
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0271480083465576,
"min": 1.0271480083465576,
"max": 2.8457155227661133,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9807.208984375,
"min": 9807.208984375,
"max": 29142.97265625,
"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": 12.7509126663208,
"min": 0.43901824951171875,
"max": 12.7509126663208,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2486.427978515625,
"min": 85.16954040527344,
"max": 2562.5078125,
"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": 0.06687533954705122,
"min": 0.06139578951143787,
"max": 0.07366724033730435,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26750135818820486,
"min": 0.24558315804575148,
"max": 0.3683362016865217,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21240230686232156,
"min": 0.1067106481173587,
"max": 0.3003532744798006,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8496092274492862,
"min": 0.4268425924694348,
"max": 1.3914636285866009,
"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": 25.454545454545453,
"min": 2.9318181818181817,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1120.0,
"min": 129.0,
"max": 1377.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.454545454545453,
"min": 2.9318181818181817,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1120.0,
"min": 129.0,
"max": 1377.0,
"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": "1674183480",
"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": "1.21.6",
"end_time_seconds": "1674183912"
},
"total": 431.6284078020001,
"count": 1,
"self": 0.439837597000178,
"children": {
"run_training.setup": {
"total": 0.10731411799997659,
"count": 1,
"self": 0.10731411799997659
},
"TrainerController.start_learning": {
"total": 431.08125608699993,
"count": 1,
"self": 0.5277822769992326,
"children": {
"TrainerController._reset_env": {
"total": 9.953858703000037,
"count": 1,
"self": 9.953858703000037
},
"TrainerController.advance": {
"total": 420.47234073400057,
"count": 18201,
"self": 0.26024327700372396,
"children": {
"env_step": {
"total": 420.21209745699684,
"count": 18201,
"self": 273.98220754198815,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.97090269802152,
"count": 18201,
"self": 1.3620616990266399,
"children": {
"TorchPolicy.evaluate": {
"total": 144.60884099899488,
"count": 18201,
"self": 31.44633926899769,
"children": {
"TorchPolicy.sample_actions": {
"total": 113.16250172999719,
"count": 18201,
"self": 113.16250172999719
}
}
}
}
},
"workers": {
"total": 0.25898721698717964,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 429.8231615099904,
"count": 18201,
"is_parallel": true,
"self": 206.8441345870009,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00912411499996324,
"count": 1,
"is_parallel": true,
"self": 0.004289642000117055,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004834472999846184,
"count": 10,
"is_parallel": true,
"self": 0.004834472999846184
}
}
},
"UnityEnvironment.step": {
"total": 0.04149644899996474,
"count": 1,
"is_parallel": true,
"self": 0.00031999899999846093,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00028484099993875134,
"count": 1,
"is_parallel": true,
"self": 0.00028484099993875134
},
"communicator.exchange": {
"total": 0.038952692000066236,
"count": 1,
"is_parallel": true,
"self": 0.038952692000066236
},
"steps_from_proto": {
"total": 0.0019389169999612932,
"count": 1,
"is_parallel": true,
"self": 0.0004440459998704682,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001494871000090825,
"count": 10,
"is_parallel": true,
"self": 0.001494871000090825
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 222.97902692298953,
"count": 18200,
"is_parallel": true,
"self": 8.263655121001534,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.815175169984741,
"count": 18200,
"is_parallel": true,
"self": 4.815175169984741
},
"communicator.exchange": {
"total": 176.95853117499632,
"count": 18200,
"is_parallel": true,
"self": 176.95853117499632
},
"steps_from_proto": {
"total": 32.941665457006934,
"count": 18200,
"is_parallel": true,
"self": 6.462570394962313,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.47909506204462,
"count": 182000,
"is_parallel": true,
"self": 26.47909506204462
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.056500006299757e-05,
"count": 1,
"self": 4.056500006299757e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 417.3022324328896,
"count": 342292,
"is_parallel": true,
"self": 9.01876375084612,
"children": {
"process_trajectory": {
"total": 240.09188460104224,
"count": 342292,
"is_parallel": true,
"self": 239.42188841404243,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6699961869998106,
"count": 4,
"is_parallel": true,
"self": 0.6699961869998106
}
}
},
"_update_policy": {
"total": 168.19158408100122,
"count": 90,
"is_parallel": true,
"self": 42.89470495599744,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.29687912500378,
"count": 4587,
"is_parallel": true,
"self": 125.29687912500378
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12723380800002815,
"count": 1,
"self": 0.0009547340000608528,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1262790739999673,
"count": 1,
"self": 0.1262790739999673
}
}
}
}
}
}
}