AGI-CEO's picture
First Push
24253e4 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.457327127456665,
"min": 1.457327127456665,
"max": 2.878257989883423,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 13209.212890625,
"min": 13209.212890625,
"max": 32262.39453125,
"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": 12.143157958984375,
"min": 0.2599720358848572,
"max": 12.143157958984375,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1226.458984375,
"min": 25.217287063598633,
"max": 1226.458984375,
"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": 13134.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.96153846153846,
"min": 3.272727272727273,
"max": 25.02,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1298.0,
"min": 144.0,
"max": 1298.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.96153846153846,
"min": 3.272727272727273,
"max": 25.02,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1298.0,
"min": 144.0,
"max": 1298.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06875177486040675,
"min": 0.06025680379614984,
"max": 0.07603026950371214,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.1375035497208135,
"min": 0.12051360759229968,
"max": 0.2193904722450551,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18343099637650975,
"min": 0.09867050275937014,
"max": 0.2995109412746102,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.3668619927530195,
"min": 0.1973410055187403,
"max": 0.7699433775509106,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 6.300097900000007e-06,
"min": 6.300097900000007e-06,
"max": 0.00029010000330000003,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.2600195800000014e-05,
"min": 1.2600195800000014e-05,
"max": 0.0007416000528,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1021,
"min": 0.1021,
"max": 0.19669999999999999,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.2042,
"min": 0.2042,
"max": 0.5472000000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00011479000000000004,
"min": 0.00011479000000000004,
"max": 0.004835329999999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0002295800000000001,
"min": 0.0002295800000000001,
"max": 0.01236528,
"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": "1715253749",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1715254250"
},
"total": 501.305148703,
"count": 1,
"self": 0.662463467000066,
"children": {
"run_training.setup": {
"total": 0.0568580799999836,
"count": 1,
"self": 0.0568580799999836
},
"TrainerController.start_learning": {
"total": 500.58582715599994,
"count": 1,
"self": 0.674762801990255,
"children": {
"TrainerController._reset_env": {
"total": 2.599754057000041,
"count": 1,
"self": 2.599754057000041
},
"TrainerController.advance": {
"total": 497.0664151250096,
"count": 18235,
"self": 0.317476338006486,
"children": {
"env_step": {
"total": 496.7489387870031,
"count": 18235,
"self": 300.3580370749902,
"children": {
"SubprocessEnvManager._take_step": {
"total": 196.05847564299188,
"count": 18235,
"self": 1.6540635669869062,
"children": {
"TorchPolicy.evaluate": {
"total": 194.40441207600497,
"count": 18235,
"self": 194.40441207600497
}
}
},
"workers": {
"total": 0.33242606902103944,
"count": 18235,
"self": 0.0,
"children": {
"worker_root": {
"total": 499.08204192401956,
"count": 18235,
"is_parallel": true,
"self": 255.98746774101926,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003127961000018331,
"count": 1,
"is_parallel": true,
"self": 0.0007282240001131868,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023997369999051443,
"count": 10,
"is_parallel": true,
"self": 0.0023997369999051443
}
}
},
"UnityEnvironment.step": {
"total": 0.07520569899998009,
"count": 1,
"is_parallel": true,
"self": 0.0006856720000314454,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043577300004926656,
"count": 1,
"is_parallel": true,
"self": 0.00043577300004926656
},
"communicator.exchange": {
"total": 0.07045510799991916,
"count": 1,
"is_parallel": true,
"self": 0.07045510799991916
},
"steps_from_proto": {
"total": 0.00362914599998021,
"count": 1,
"is_parallel": true,
"self": 0.0004136249998509811,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003215521000129229,
"count": 10,
"is_parallel": true,
"self": 0.003215521000129229
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 243.0945741830003,
"count": 18234,
"is_parallel": true,
"self": 10.927356715032147,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.812182951011664,
"count": 18234,
"is_parallel": true,
"self": 5.812182951011664
},
"communicator.exchange": {
"total": 189.2133915319631,
"count": 18234,
"is_parallel": true,
"self": 189.2133915319631
},
"steps_from_proto": {
"total": 37.14164298499338,
"count": 18234,
"is_parallel": true,
"self": 7.264089770991404,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.877553214001978,
"count": 182340,
"is_parallel": true,
"self": 29.877553214001978
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001614740001514292,
"count": 1,
"self": 0.0001614740001514292,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 492.62776834402496,
"count": 541606,
"is_parallel": true,
"self": 11.891571274006196,
"children": {
"process_trajectory": {
"total": 229.13732035301894,
"count": 541606,
"is_parallel": true,
"self": 227.9679424540193,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1693778989996417,
"count": 4,
"is_parallel": true,
"self": 1.1693778989996417
}
}
},
"_update_policy": {
"total": 251.59887671699983,
"count": 45,
"is_parallel": true,
"self": 66.57828762700603,
"children": {
"TorchPPOOptimizer.update": {
"total": 185.0205890899938,
"count": 4590,
"is_parallel": true,
"self": 185.0205890899938
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.24473369799989086,
"count": 1,
"self": 0.0038125029998354876,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24092119500005538,
"count": 1,
"self": 0.24092119500005538
}
}
}
}
}
}
}