alex-daly's picture
2M training partial
4cf498e verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.15555311739444733,
"min": 0.15346011519432068,
"max": 1.422135353088379,
"count": 74
},
"Pyramids.Policy.Entropy.sum": {
"value": 4649.17138671875,
"min": 4596.4375,
"max": 43141.8984375,
"count": 74
},
"Pyramids.Step.mean": {
"value": 2219936.0,
"min": 29952.0,
"max": 2219936.0,
"count": 74
},
"Pyramids.Step.sum": {
"value": 2219936.0,
"min": 29952.0,
"max": 2219936.0,
"count": 74
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.8239283561706543,
"min": -0.08849889039993286,
"max": 0.8830233216285706,
"count": 74
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 249.65029907226562,
"min": -21.328231811523438,
"max": 270.20513916015625,
"count": 74
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.011012603528797626,
"min": -0.018887344747781754,
"max": 0.5779843330383301,
"count": 74
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -3.3368189334869385,
"min": -5.345118522644043,
"max": 136.98228454589844,
"count": 74
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06482129398292662,
"min": 0.06372850304986868,
"max": 0.0733717020803375,
"count": 74
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9074981157609727,
"min": 0.49391542951845363,
"max": 1.0901601150011024,
"count": 74
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.012689866814374302,
"min": 0.0010723435507997375,
"max": 0.017420825411959197,
"count": 74
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.17765813540124023,
"min": 0.012868122609596851,
"max": 0.24389155576742874,
"count": 74
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.944262351914997e-05,
"min": 7.944262351914997e-05,
"max": 0.00029838354339596195,
"count": 74
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0011121967292680997,
"min": 0.0011121967292680997,
"max": 0.004010805463064866,
"count": 74
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.12648085,
"min": 0.12648085,
"max": 0.19946118095238097,
"count": 74
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.7707319,
"min": 1.3962282666666668,
"max": 2.8275687,
"count": 74
},
"Pyramids.Policy.Beta.mean": {
"value": 0.002655436915,
"min": 0.002655436915,
"max": 0.009946171977142856,
"count": 74
},
"Pyramids.Policy.Beta.sum": {
"value": 0.03717611681,
"min": 0.03717611681,
"max": 0.13369981982,
"count": 74
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.006534861866384745,
"min": 0.006534861866384745,
"max": 0.39515992999076843,
"count": 74
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.0914880633354187,
"min": 0.0914880633354187,
"max": 2.7661194801330566,
"count": 74
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 230.94656488549617,
"min": 208.84285714285716,
"max": 999.0,
"count": 74
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30254.0,
"min": 15984.0,
"max": 32684.0,
"count": 74
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7536625757472206,
"min": -1.0000000521540642,
"max": 1.7911571314292294,
"count": 74
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 229.7297974228859,
"min": -30.999201610684395,
"max": 258.4411981329322,
"count": 74
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7536625757472206,
"min": -1.0000000521540642,
"max": 1.7911571314292294,
"count": 74
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 229.7297974228859,
"min": -30.999201610684395,
"max": 258.4411981329322,
"count": 74
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.015532971826061616,
"min": 0.014683143399694624,
"max": 8.150948827154934,
"count": 74
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.034819309214072,
"min": 1.9142058067955077,
"max": 130.41518123447895,
"count": 74
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 74
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 74
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1737994952",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1738000616"
},
"total": 5664.924440594,
"count": 1,
"self": 0.4490465269991546,
"children": {
"run_training.setup": {
"total": 0.026352270999950633,
"count": 1,
"self": 0.026352270999950633
},
"TrainerController.start_learning": {
"total": 5664.4490417960005,
"count": 1,
"self": 3.022323507049805,
"children": {
"TrainerController._reset_env": {
"total": 2.6295346870001595,
"count": 1,
"self": 2.6295346870001595
},
"TrainerController.advance": {
"total": 5658.562026758951,
"count": 144844,
"self": 3.3747616979344457,
"children": {
"env_step": {
"total": 4094.684346398887,
"count": 144844,
"self": 3752.448692930124,
"children": {
"SubprocessEnvManager._take_step": {
"total": 340.37003078584644,
"count": 144844,
"self": 10.390870943617301,
"children": {
"TorchPolicy.evaluate": {
"total": 329.97915984222914,
"count": 139005,
"self": 329.97915984222914
}
}
},
"workers": {
"total": 1.8656226829170919,
"count": 144843,
"self": 0.0,
"children": {
"worker_root": {
"total": 5652.6065506130735,
"count": 144843,
"is_parallel": true,
"self": 2161.2657783041645,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0027401769998505188,
"count": 1,
"is_parallel": true,
"self": 0.0008068399999956455,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019333369998548733,
"count": 8,
"is_parallel": true,
"self": 0.0019333369998548733
}
}
},
"UnityEnvironment.step": {
"total": 0.04677799799992499,
"count": 1,
"is_parallel": true,
"self": 0.0005188249997445382,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004928350001591753,
"count": 1,
"is_parallel": true,
"self": 0.0004928350001591753
},
"communicator.exchange": {
"total": 0.044096147999880486,
"count": 1,
"is_parallel": true,
"self": 0.044096147999880486
},
"steps_from_proto": {
"total": 0.001670190000140792,
"count": 1,
"is_parallel": true,
"self": 0.00036669900009655976,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013034910000442324,
"count": 8,
"is_parallel": true,
"self": 0.0013034910000442324
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 3491.340772308909,
"count": 144842,
"is_parallel": true,
"self": 69.98356398698388,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 50.25589264988707,
"count": 144842,
"is_parallel": true,
"self": 50.25589264988707
},
"communicator.exchange": {
"total": 3161.012008203217,
"count": 144842,
"is_parallel": true,
"self": 3161.012008203217
},
"steps_from_proto": {
"total": 210.08930746882106,
"count": 144842,
"is_parallel": true,
"self": 41.99505623329992,
"children": {
"_process_rank_one_or_two_observation": {
"total": 168.09425123552114,
"count": 1158736,
"is_parallel": true,
"self": 168.09425123552114
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1560.50291866213,
"count": 144843,
"self": 6.369362325192469,
"children": {
"process_trajectory": {
"total": 299.5470165309325,
"count": 144843,
"self": 299.1246236469319,
"children": {
"RLTrainer._checkpoint": {
"total": 0.42239288400060104,
"count": 4,
"self": 0.42239288400060104
}
}
},
"_update_policy": {
"total": 1254.586539806005,
"count": 1033,
"self": 693.5514105959803,
"children": {
"TorchPPOOptimizer.update": {
"total": 561.0351292100247,
"count": 50694,
"self": 561.0351292100247
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3049993867753074e-06,
"count": 1,
"self": 1.3049993867753074e-06
},
"TrainerController._save_models": {
"total": 0.23515553800007183,
"count": 1,
"self": 0.0029102709995640907,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23224526700050774,
"count": 1,
"self": 0.23224526700050774
}
}
}
}
}
}
}