mahmoud-mohey's picture
First trial
212e066
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.2816214859485626,
"min": 0.27325060963630676,
"max": 1.447108507156372,
"count": 40
},
"Pyramids.Policy.Entropy.sum": {
"value": 8484.6923828125,
"min": 8193.3017578125,
"max": 43899.484375,
"count": 40
},
"Pyramids.Step.mean": {
"value": 1199944.0,
"min": 29952.0,
"max": 1199944.0,
"count": 40
},
"Pyramids.Step.sum": {
"value": 1199944.0,
"min": 29952.0,
"max": 1199944.0,
"count": 40
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.641365110874176,
"min": -0.11645389348268509,
"max": 0.6860062479972839,
"count": 40
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 182.14768981933594,
"min": -28.065387725830078,
"max": 196.8837890625,
"count": 40
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0178033709526062,
"min": -0.00929284654557705,
"max": 0.225004643201828,
"count": 40
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.056157112121582,
"min": -2.5927042961120605,
"max": 54.22611999511719,
"count": 40
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06766902339932997,
"min": 0.0650183567001174,
"max": 0.07413154792794516,
"count": 40
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9473663275906196,
"min": 0.4989679115433005,
"max": 1.0472376360654987,
"count": 40
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01697522836426894,
"min": 0.0006247077437635777,
"max": 0.01713264944976092,
"count": 40
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23765319709976515,
"min": 0.00812120066892651,
"max": 0.2569897417464138,
"count": 40
},
"Pyramids.Policy.LearningRate.mean": {
"value": 3.7445451804226198e-06,
"min": 3.7445451804226198e-06,
"max": 0.0002959588584899048,
"count": 40
},
"Pyramids.Policy.LearningRate.sum": {
"value": 5.242363252591668e-05,
"min": 5.242363252591668e-05,
"max": 0.0036226571924476664,
"count": 40
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10124814880952382,
"min": 0.10124814880952382,
"max": 0.1986529523809524,
"count": 40
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4174740833333335,
"min": 1.3905706666666668,
"max": 2.6075523333333335,
"count": 40
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00013469006607142857,
"min": 0.00013469006607142857,
"max": 0.00986542994285714,
"count": 40
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0018856609250000001,
"min": 0.0018856609250000001,
"max": 0.12077447809999999,
"count": 40
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007941853255033493,
"min": 0.007908061146736145,
"max": 0.415669709444046,
"count": 40
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1111859455704689,
"min": 0.11071285605430603,
"max": 2.9096879959106445,
"count": 40
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 294.36893203883494,
"min": 274.6509433962264,
"max": 999.0,
"count": 40
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30320.0,
"min": 15984.0,
"max": 33038.0,
"count": 40
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.686211634174134,
"min": -1.0000000521540642,
"max": 1.7018968920732283,
"count": 40
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 173.6797983199358,
"min": -29.898201644420624,
"max": 184.77499793469906,
"count": 40
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.686211634174134,
"min": -1.0000000521540642,
"max": 1.7018968920732283,
"count": 40
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 173.6797983199358,
"min": -29.898201644420624,
"max": 184.77499793469906,
"count": 40
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.024442765250286647,
"min": 0.022999434261846374,
"max": 9.523486039601266,
"count": 40
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.5176048207795247,
"min": 2.381915781501448,
"max": 152.37577663362026,
"count": 40
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1674325890",
"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": "1674328335"
},
"total": 2444.817424825,
"count": 1,
"self": 0.4274704730000849,
"children": {
"run_training.setup": {
"total": 0.11824862000003122,
"count": 1,
"self": 0.11824862000003122
},
"TrainerController.start_learning": {
"total": 2444.271705732,
"count": 1,
"self": 1.424217562974718,
"children": {
"TrainerController._reset_env": {
"total": 6.8738629819999915,
"count": 1,
"self": 6.8738629819999915
},
"TrainerController.advance": {
"total": 2435.8780134030258,
"count": 76972,
"self": 1.4874208402252407,
"children": {
"env_step": {
"total": 1673.3590310878744,
"count": 76972,
"self": 1556.884214595943,
"children": {
"SubprocessEnvManager._take_step": {
"total": 115.61947711898802,
"count": 76972,
"self": 4.774968489137791,
"children": {
"TorchPolicy.evaluate": {
"total": 110.84450862985022,
"count": 75059,
"self": 37.589818540806846,
"children": {
"TorchPolicy.sample_actions": {
"total": 73.25469008904338,
"count": 75059,
"self": 73.25469008904338
}
}
}
}
},
"workers": {
"total": 0.8553393729434902,
"count": 76972,
"self": 0.0,
"children": {
"worker_root": {
"total": 2439.99166084691,
"count": 76972,
"is_parallel": true,
"self": 993.0030073088096,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0016060819998529041,
"count": 1,
"is_parallel": true,
"self": 0.0005645320002258813,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010415499996270228,
"count": 8,
"is_parallel": true,
"self": 0.0010415499996270228
}
}
},
"UnityEnvironment.step": {
"total": 0.0458810490003998,
"count": 1,
"is_parallel": true,
"self": 0.0005086400001346192,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005010350000702601,
"count": 1,
"is_parallel": true,
"self": 0.0005010350000702601
},
"communicator.exchange": {
"total": 0.04316214900018167,
"count": 1,
"is_parallel": true,
"self": 0.04316214900018167
},
"steps_from_proto": {
"total": 0.001709225000013248,
"count": 1,
"is_parallel": true,
"self": 0.0004373009996925248,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012719240003207233,
"count": 8,
"is_parallel": true,
"self": 0.0012719240003207233
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1446.9886535381002,
"count": 76971,
"is_parallel": true,
"self": 31.65827170807006,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.12121521501558,
"count": 76971,
"is_parallel": true,
"self": 25.12121521501558
},
"communicator.exchange": {
"total": 1277.6611165719955,
"count": 76971,
"is_parallel": true,
"self": 1277.6611165719955
},
"steps_from_proto": {
"total": 112.54805004301897,
"count": 76971,
"is_parallel": true,
"self": 24.446230012097203,
"children": {
"_process_rank_one_or_two_observation": {
"total": 88.10182003092177,
"count": 615768,
"is_parallel": true,
"self": 88.10182003092177
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 761.0315614749261,
"count": 76972,
"self": 2.6816516639114525,
"children": {
"process_trajectory": {
"total": 167.05535639602613,
"count": 76972,
"self": 166.77351540902646,
"children": {
"RLTrainer._checkpoint": {
"total": 0.28184098699966853,
"count": 2,
"self": 0.28184098699966853
}
}
},
"_update_policy": {
"total": 591.2945534149885,
"count": 546,
"self": 226.89345218001654,
"children": {
"TorchPPOOptimizer.update": {
"total": 364.401101234972,
"count": 27321,
"self": 364.401101234972
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0310004654456861e-06,
"count": 1,
"self": 1.0310004654456861e-06
},
"TrainerController._save_models": {
"total": 0.0956107529991641,
"count": 1,
"self": 0.001357368999379105,
"children": {
"RLTrainer._checkpoint": {
"total": 0.094253383999785,
"count": 1,
"self": 0.094253383999785
}
}
}
}
}
}
}