Junfeng's picture
First Push
22ec2bd
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.2884405851364136,
"min": 0.2884405851364136,
"max": 1.508360743522644,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 8837.8193359375,
"min": 8837.8193359375,
"max": 45757.6328125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989949.0,
"min": 29952.0,
"max": 989949.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989949.0,
"min": 29952.0,
"max": 989949.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5964992046356201,
"min": -0.09088549762964249,
"max": 0.6323741674423218,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 167.61627197265625,
"min": -21.903404235839844,
"max": 180.8590087890625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.010587316006422043,
"min": -0.006445754785090685,
"max": 0.4139411449432373,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.9750356674194336,
"min": -1.8434858322143555,
"max": 98.10404968261719,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07047410188048768,
"min": 0.06425478990412371,
"max": 0.07771052935728723,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9866374263268276,
"min": 0.47973262145680423,
"max": 1.0911504749799896,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01555370194477118,
"min": 0.0005119744342892493,
"max": 0.017190089765617377,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2177518272267965,
"min": 0.006143693211470991,
"max": 0.2406612567186433,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.367604687021427e-06,
"min": 7.367604687021427e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010314646561829997,
"min": 0.00010314646561829997,
"max": 0.0035070566309811997,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10245583571428572,
"min": 0.10245583571428572,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4343817,
"min": 1.3886848,
"max": 2.5690188000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002553379878571428,
"min": 0.0002553379878571428,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035747318299999987,
"min": 0.0035747318299999987,
"max": 0.11692497812,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01181162428110838,
"min": 0.011641000397503376,
"max": 0.3936607539653778,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.16536274552345276,
"min": 0.16297399997711182,
"max": 2.7556252479553223,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 326.86021505376345,
"min": 285.49,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30398.0,
"min": 15984.0,
"max": 32796.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6086107385094448,
"min": -1.0000000521540642,
"max": 1.715425727391007,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 149.60079868137836,
"min": -30.60700172185898,
"max": 173.2579984664917,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6086107385094448,
"min": -1.0000000521540642,
"max": 1.715425727391007,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 149.60079868137836,
"min": -30.60700172185898,
"max": 173.2579984664917,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03998598419204955,
"min": 0.034743003916536515,
"max": 7.755236975848675,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.7186965298606083,
"min": 3.5090433955701883,
"max": 124.0837916135788,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1674462155",
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1674464345"
},
"total": 2189.575114166,
"count": 1,
"self": 0.425237140000263,
"children": {
"run_training.setup": {
"total": 0.09808946499970261,
"count": 1,
"self": 0.09808946499970261
},
"TrainerController.start_learning": {
"total": 2189.051787561,
"count": 1,
"self": 1.4405442419970313,
"children": {
"TrainerController._reset_env": {
"total": 6.053127312000015,
"count": 1,
"self": 6.053127312000015
},
"TrainerController.advance": {
"total": 2181.472340108003,
"count": 64080,
"self": 1.490739988043515,
"children": {
"env_step": {
"total": 1537.0009701349795,
"count": 64080,
"self": 1422.4418609618629,
"children": {
"SubprocessEnvManager._take_step": {
"total": 113.65756988703652,
"count": 64080,
"self": 4.62257288494493,
"children": {
"TorchPolicy.evaluate": {
"total": 109.03499700209159,
"count": 62555,
"self": 36.05279446901159,
"children": {
"TorchPolicy.sample_actions": {
"total": 72.98220253308,
"count": 62555,
"self": 72.98220253308
}
}
}
}
},
"workers": {
"total": 0.9015392860801512,
"count": 64080,
"self": 0.0,
"children": {
"worker_root": {
"total": 2184.0355192139596,
"count": 64080,
"is_parallel": true,
"self": 870.3570296349958,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002008974000091257,
"count": 1,
"is_parallel": true,
"self": 0.0007741569997961051,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001234817000295152,
"count": 8,
"is_parallel": true,
"self": 0.001234817000295152
}
}
},
"UnityEnvironment.step": {
"total": 0.04752951699992991,
"count": 1,
"is_parallel": true,
"self": 0.00047890399991956656,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005258999999568914,
"count": 1,
"is_parallel": true,
"self": 0.0005258999999568914
},
"communicator.exchange": {
"total": 0.04486304200008817,
"count": 1,
"is_parallel": true,
"self": 0.04486304200008817
},
"steps_from_proto": {
"total": 0.0016616709999652812,
"count": 1,
"is_parallel": true,
"self": 0.0004198480000923155,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012418229998729657,
"count": 8,
"is_parallel": true,
"self": 0.0012418229998729657
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1313.6784895789638,
"count": 64079,
"is_parallel": true,
"self": 28.70720384791548,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.86776735598596,
"count": 64079,
"is_parallel": true,
"self": 24.86776735598596
},
"communicator.exchange": {
"total": 1153.1604650939676,
"count": 64079,
"is_parallel": true,
"self": 1153.1604650939676
},
"steps_from_proto": {
"total": 106.94305328109476,
"count": 64079,
"is_parallel": true,
"self": 24.236038940191065,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.7070143409037,
"count": 512632,
"is_parallel": true,
"self": 82.7070143409037
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 642.9806299849802,
"count": 64080,
"self": 2.6670462039446647,
"children": {
"process_trajectory": {
"total": 148.86285855903407,
"count": 64080,
"self": 148.67522911803462,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18762944099944434,
"count": 2,
"self": 0.18762944099944434
}
}
},
"_update_policy": {
"total": 491.45072522200144,
"count": 449,
"self": 183.7321573280683,
"children": {
"TorchPPOOptimizer.update": {
"total": 307.71856789393314,
"count": 22836,
"self": 307.71856789393314
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.899996828404255e-07,
"count": 1,
"self": 8.899996828404255e-07
},
"TrainerController._save_models": {
"total": 0.08577500899991719,
"count": 1,
"self": 0.00136669699986669,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0844083120000505,
"count": 1,
"self": 0.0844083120000505
}
}
}
}
}
}
}