Dewa's picture
First Push
3c4af63
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9655676484107971,
"min": 0.9655676484107971,
"max": 2.85941219329834,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9229.861328125,
"min": 9229.861328125,
"max": 29314.693359375,
"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": 13.29674243927002,
"min": 0.451429158449173,
"max": 13.41246509552002,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2592.86474609375,
"min": 87.57725524902344,
"max": 2736.142822265625,
"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": 0.07063096940948846,
"min": 0.061182602279358456,
"max": 0.07300266965381418,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28252387763795384,
"min": 0.25736518071704156,
"max": 0.3609714918306517,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1927444788755155,
"min": 0.13636816305669902,
"max": 0.3021557318813661,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.770977915502062,
"min": 0.5454726522267961,
"max": 1.5107786594068304,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.616409730600001e-05,
"min": 1.616409730600001e-05,
"max": 0.0005837640027059999,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 6.465638922400003e-05,
"min": 6.465638922400003e-05,
"max": 0.00277032003828,
"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": 25.295454545454547,
"min": 3.75,
"max": 26.618181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 165.0,
"max": 1464.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.75,
"max": 26.618181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 165.0,
"max": 1464.0,
"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": "1682063785",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1682064255"
},
"total": 470.00723276400004,
"count": 1,
"self": 0.44155065399991145,
"children": {
"run_training.setup": {
"total": 0.11431478800022887,
"count": 1,
"self": 0.11431478800022887
},
"TrainerController.start_learning": {
"total": 469.4513673219999,
"count": 1,
"self": 0.6005102539952532,
"children": {
"TrainerController._reset_env": {
"total": 4.026395816999866,
"count": 1,
"self": 4.026395816999866
},
"TrainerController.advance": {
"total": 464.68618549500434,
"count": 18201,
"self": 0.2855112959732651,
"children": {
"env_step": {
"total": 464.4006741990311,
"count": 18201,
"self": 341.98124458802704,
"children": {
"SubprocessEnvManager._take_step": {
"total": 122.12853933701581,
"count": 18201,
"self": 1.7573649970131555,
"children": {
"TorchPolicy.evaluate": {
"total": 120.37117434000265,
"count": 18201,
"self": 120.37117434000265
}
}
},
"workers": {
"total": 0.2908902739882251,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 467.78613116399856,
"count": 18201,
"is_parallel": true,
"self": 212.10860363504207,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005039870000018709,
"count": 1,
"is_parallel": true,
"self": 0.0032698139998501574,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017700560001685517,
"count": 10,
"is_parallel": true,
"self": 0.0017700560001685517
}
}
},
"UnityEnvironment.step": {
"total": 0.03715702699992107,
"count": 1,
"is_parallel": true,
"self": 0.0006120629996075877,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00028923500030941796,
"count": 1,
"is_parallel": true,
"self": 0.00028923500030941796
},
"communicator.exchange": {
"total": 0.03432296700020743,
"count": 1,
"is_parallel": true,
"self": 0.03432296700020743
},
"steps_from_proto": {
"total": 0.0019327619997966394,
"count": 1,
"is_parallel": true,
"self": 0.00040437699908579816,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015283850007108413,
"count": 10,
"is_parallel": true,
"self": 0.0015283850007108413
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 255.6775275289565,
"count": 18200,
"is_parallel": true,
"self": 10.074589430961169,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.467039435004153,
"count": 18200,
"is_parallel": true,
"self": 5.467039435004153
},
"communicator.exchange": {
"total": 207.38175636597862,
"count": 18200,
"is_parallel": true,
"self": 207.38175636597862
},
"steps_from_proto": {
"total": 32.75414229701255,
"count": 18200,
"is_parallel": true,
"self": 6.558382696096487,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.195759600916062,
"count": 182000,
"is_parallel": true,
"self": 26.195759600916062
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015214300037769135,
"count": 1,
"self": 0.00015214300037769135,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 461.1631693478744,
"count": 417329,
"is_parallel": true,
"self": 10.019942683985391,
"children": {
"process_trajectory": {
"total": 254.4450650798899,
"count": 417329,
"is_parallel": true,
"self": 253.15622889288989,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2888361870000153,
"count": 4,
"is_parallel": true,
"self": 1.2888361870000153
}
}
},
"_update_policy": {
"total": 196.69816158399908,
"count": 90,
"is_parallel": true,
"self": 73.78580364700929,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.91235793698979,
"count": 4584,
"is_parallel": true,
"self": 122.91235793698979
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1381236130000616,
"count": 1,
"self": 0.0010043029997177655,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13711931000034383,
"count": 1,
"self": 0.13711931000034383
}
}
}
}
}
}
}