Winmodel's picture
Push to Hub
c330bc7
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4641125798225403,
"min": 0.44791874289512634,
"max": 1.5325313806533813,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13841.693359375,
"min": 13423.228515625,
"max": 46490.87109375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989942.0,
"min": 29952.0,
"max": 989942.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989942.0,
"min": 29952.0,
"max": 989942.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6023756265640259,
"min": -0.1066809743642807,
"max": 0.6469970345497131,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 171.07467651367188,
"min": -25.60343360900879,
"max": 183.74716186523438,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.04529917985200882,
"min": -0.04529917985200882,
"max": 0.17037346959114075,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -12.864967346191406,
"min": -12.864967346191406,
"max": 41.06000518798828,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06996993023356134,
"min": 0.0649624934236236,
"max": 0.07454991246123832,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9795790232698588,
"min": 0.5218493872286682,
"max": 1.0684968969823485,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.017504917964245015,
"min": 0.0007914430660484285,
"max": 0.017504917964245015,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2450688514994302,
"min": 0.007914430660484285,
"max": 0.24766564054880288,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.633426026985712e-06,
"min": 7.633426026985712e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010686796437779997,
"min": 0.00010686796437779997,
"max": 0.0032604530131824004,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10254444285714288,
"min": 0.10254444285714288,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4356222000000003,
"min": 1.3886848,
"max": 2.4846883,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002641898414285714,
"min": 0.0002641898414285714,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036986577799999996,
"min": 0.0036986577799999996,
"max": 0.10870307824,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00845095980912447,
"min": 0.00845095980912447,
"max": 0.28175655007362366,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.11831343919038773,
"min": 0.11831343919038773,
"max": 1.972295880317688,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 301.659793814433,
"min": 290.3921568627451,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29261.0,
"min": 15984.0,
"max": 33046.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6983401907473494,
"min": -1.0000000521540642,
"max": 1.7096078261440875,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 164.7389985024929,
"min": -30.6896016523242,
"max": 174.37999826669693,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6983401907473494,
"min": -1.0000000521540642,
"max": 1.7096078261440875,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 164.7389985024929,
"min": -30.6896016523242,
"max": 174.37999826669693,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.026422598962696057,
"min": 0.026422598962696057,
"max": 5.91017185524106,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.5629920993815176,
"min": 2.5629920993815176,
"max": 94.56274968385696,
"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": "1689068926",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "0.31.0.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": "1689071376"
},
"total": 2449.587901977,
"count": 1,
"self": 1.4568178669996996,
"children": {
"run_training.setup": {
"total": 0.03943556799981707,
"count": 1,
"self": 0.03943556799981707
},
"TrainerController.start_learning": {
"total": 2448.0916485420003,
"count": 1,
"self": 1.7168541270575588,
"children": {
"TrainerController._reset_env": {
"total": 4.12018770099985,
"count": 1,
"self": 4.12018770099985
},
"TrainerController.advance": {
"total": 2442.1048898389427,
"count": 64026,
"self": 1.7234061439748984,
"children": {
"env_step": {
"total": 1761.7765228129726,
"count": 64026,
"self": 1631.7513606929829,
"children": {
"SubprocessEnvManager._take_step": {
"total": 128.98592787298162,
"count": 64026,
"self": 5.2183239699677415,
"children": {
"TorchPolicy.evaluate": {
"total": 123.76760390301388,
"count": 62555,
"self": 123.76760390301388
}
}
},
"workers": {
"total": 1.039234247008153,
"count": 64026,
"self": 0.0,
"children": {
"worker_root": {
"total": 2441.7744158809696,
"count": 64026,
"is_parallel": true,
"self": 939.0422954939731,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017705660000046919,
"count": 1,
"is_parallel": true,
"self": 0.0005542149999655521,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012163510000391398,
"count": 8,
"is_parallel": true,
"self": 0.0012163510000391398
}
}
},
"UnityEnvironment.step": {
"total": 0.04841730600014671,
"count": 1,
"is_parallel": true,
"self": 0.0005524270002297271,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004620950001026358,
"count": 1,
"is_parallel": true,
"self": 0.0004620950001026358
},
"communicator.exchange": {
"total": 0.045567709999886574,
"count": 1,
"is_parallel": true,
"self": 0.045567709999886574
},
"steps_from_proto": {
"total": 0.001835073999927772,
"count": 1,
"is_parallel": true,
"self": 0.0003411010002309922,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014939729996967799,
"count": 8,
"is_parallel": true,
"self": 0.0014939729996967799
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1502.7321203869965,
"count": 64025,
"is_parallel": true,
"self": 36.53462980104291,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.855004875009172,
"count": 64025,
"is_parallel": true,
"self": 23.855004875009172
},
"communicator.exchange": {
"total": 1330.0608460999972,
"count": 64025,
"is_parallel": true,
"self": 1330.0608460999972
},
"steps_from_proto": {
"total": 112.2816396109472,
"count": 64025,
"is_parallel": true,
"self": 22.19753083797127,
"children": {
"_process_rank_one_or_two_observation": {
"total": 90.08410877297592,
"count": 512200,
"is_parallel": true,
"self": 90.08410877297592
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 678.6049608819949,
"count": 64026,
"self": 3.167153046024623,
"children": {
"process_trajectory": {
"total": 116.10269459996834,
"count": 64026,
"self": 115.78434524996828,
"children": {
"RLTrainer._checkpoint": {
"total": 0.31834935000006226,
"count": 2,
"self": 0.31834935000006226
}
}
},
"_update_policy": {
"total": 559.3351132360019,
"count": 449,
"self": 360.51952956699733,
"children": {
"TorchPPOOptimizer.update": {
"total": 198.81558366900458,
"count": 22827,
"self": 198.81558366900458
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2880000213044696e-06,
"count": 1,
"self": 1.2880000213044696e-06
},
"TrainerController._save_models": {
"total": 0.1497155870001734,
"count": 1,
"self": 0.0018468389998815837,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14786874800029182,
"count": 1,
"self": 0.14786874800029182
}
}
}
}
}
}
}