pyramids_test1 / run_logs /timers.json
c-g's picture
commit1
97a4804
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5021506547927856,
"min": 0.5021506547927856,
"max": 1.4920095205307007,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 14984.17578125,
"min": 14984.17578125,
"max": 45261.6015625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989965.0,
"min": 29952.0,
"max": 989965.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989965.0,
"min": 29952.0,
"max": 989965.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.22611448168754578,
"min": -0.10216780751943588,
"max": 0.2841082513332367,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 58.3375358581543,
"min": -24.724609375,
"max": 73.86814880371094,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.9184799790382385,
"min": -0.29537999629974365,
"max": 1.2115176916122437,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 236.96783447265625,
"min": -76.50341796875,
"max": 314.9945983886719,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06821941310010429,
"min": 0.06513066821757496,
"max": 0.07527306955424806,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9550717834014602,
"min": 0.492703045007837,
"max": 1.0722641541015394,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.15624019664080283,
"min": 0.001007773937901953,
"max": 0.22454367401983794,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 2.1873627529712394,
"min": 0.007902372321903637,
"max": 3.368155110297569,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.500118928564282e-06,
"min": 7.500118928564282e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010500166499989995,
"min": 0.00010500166499989995,
"max": 0.0032572250142584,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10250000714285715,
"min": 0.10250000714285715,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4350001000000001,
"min": 1.3691136000000002,
"max": 2.4852578000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002597507135714285,
"min": 0.0002597507135714285,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003636509989999999,
"min": 0.003636509989999999,
"max": 0.10859558584,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00944130215793848,
"min": 0.008440539240837097,
"max": 0.3676963448524475,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.13217823207378387,
"min": 0.11816754937171936,
"max": 2.5738744735717773,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 549.0188679245283,
"min": 500.7142857142857,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29098.0,
"min": 15984.0,
"max": 32366.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.9609962642468788,
"min": -1.0000000521540642,
"max": 1.072667901246053,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 51.893798269331455,
"min": -32.000001668930054,
"max": 64.23039814829826,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.9609962642468788,
"min": -1.0000000521540642,
"max": 1.072667901246053,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 51.893798269331455,
"min": -32.000001668930054,
"max": 64.23039814829826,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.05391255627856245,
"min": 0.051680048903906525,
"max": 8.046361776068807,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.9112780390423723,
"min": 2.53232239629142,
"max": 128.7417884171009,
"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": "1696244276",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "0.31.0.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": "1696246570"
},
"total": 2294.185716109,
"count": 1,
"self": 0.5305372720004016,
"children": {
"run_training.setup": {
"total": 0.04022258200006945,
"count": 1,
"self": 0.04022258200006945
},
"TrainerController.start_learning": {
"total": 2293.614956255,
"count": 1,
"self": 1.3827964190140847,
"children": {
"TrainerController._reset_env": {
"total": 5.6247360479999315,
"count": 1,
"self": 5.6247360479999315
},
"TrainerController.advance": {
"total": 2286.513123790987,
"count": 63493,
"self": 1.3462596818712882,
"children": {
"env_step": {
"total": 1610.2826746760588,
"count": 63493,
"self": 1501.2480643811186,
"children": {
"SubprocessEnvManager._take_step": {
"total": 108.19846278290652,
"count": 63493,
"self": 4.682967251962509,
"children": {
"TorchPolicy.evaluate": {
"total": 103.51549553094401,
"count": 62557,
"self": 103.51549553094401
}
}
},
"workers": {
"total": 0.8361475120336763,
"count": 63493,
"self": 0.0,
"children": {
"worker_root": {
"total": 2288.418504687979,
"count": 63493,
"is_parallel": true,
"self": 901.439076575052,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002766390000033425,
"count": 1,
"is_parallel": true,
"self": 0.0007953129997986252,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019710770002348,
"count": 8,
"is_parallel": true,
"self": 0.0019710770002348
}
}
},
"UnityEnvironment.step": {
"total": 0.08629489800000556,
"count": 1,
"is_parallel": true,
"self": 0.0006624949999149976,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005493070000284206,
"count": 1,
"is_parallel": true,
"self": 0.0005493070000284206
},
"communicator.exchange": {
"total": 0.08214933399995061,
"count": 1,
"is_parallel": true,
"self": 0.08214933399995061
},
"steps_from_proto": {
"total": 0.0029337620001115283,
"count": 1,
"is_parallel": true,
"self": 0.0004008160001376382,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00253294599997389,
"count": 8,
"is_parallel": true,
"self": 0.00253294599997389
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1386.9794281129268,
"count": 63492,
"is_parallel": true,
"self": 34.174127390876265,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.104340074013408,
"count": 63492,
"is_parallel": true,
"self": 23.104340074013408
},
"communicator.exchange": {
"total": 1224.1752410320287,
"count": 63492,
"is_parallel": true,
"self": 1224.1752410320287
},
"steps_from_proto": {
"total": 105.52571961600847,
"count": 63492,
"is_parallel": true,
"self": 20.615875372899836,
"children": {
"_process_rank_one_or_two_observation": {
"total": 84.90984424310864,
"count": 507936,
"is_parallel": true,
"self": 84.90984424310864
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 674.8841894330565,
"count": 63493,
"self": 2.637011567025638,
"children": {
"process_trajectory": {
"total": 111.94504011603544,
"count": 63493,
"self": 111.73689922703511,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20814088900033312,
"count": 2,
"self": 0.20814088900033312
}
}
},
"_update_policy": {
"total": 560.3021377499954,
"count": 443,
"self": 366.5897470269949,
"children": {
"TorchPPOOptimizer.update": {
"total": 193.71239072300045,
"count": 22818,
"self": 193.71239072300045
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3089993444737047e-06,
"count": 1,
"self": 1.3089993444737047e-06
},
"TrainerController._save_models": {
"total": 0.09429868799998076,
"count": 1,
"self": 0.0014279840006565792,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09287070399932418,
"count": 1,
"self": 0.09287070399932418
}
}
}
}
}
}
}