ppo-Pyramids / run_logs /timers.json
mili7522's picture
Suggested config
dd321e1
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5744317173957825,
"min": 0.5560988783836365,
"max": 1.541096806526184,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 17269.71484375,
"min": 16718.556640625,
"max": 46750.7109375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989894.0,
"min": 29952.0,
"max": 989894.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989894.0,
"min": 29952.0,
"max": 989894.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4434658885002136,
"min": -0.161443829536438,
"max": 0.4528704583644867,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 118.84886169433594,
"min": -38.26218795776367,
"max": 121.86485290527344,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.07148974388837814,
"min": -0.07148974388837814,
"max": 0.15823990106582642,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -19.159252166748047,
"min": -19.159252166748047,
"max": 37.977577209472656,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0647841854797789,
"min": 0.06287878963976305,
"max": 0.0729048290296542,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9069785967169046,
"min": 0.5033777054289192,
"max": 1.0374755085601162,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015943083010302662,
"min": 0.0001342592577150624,
"max": 0.015943083010302662,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22320316214423727,
"min": 0.0016111110925807485,
"max": 0.22320316214423727,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.752783130057144e-06,
"min": 7.752783130057144e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010853896382080001,
"min": 0.00010853896382080001,
"max": 0.0031174924608358993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10258422857142858,
"min": 0.10258422857142858,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4361792000000002,
"min": 1.3886848,
"max": 2.3592476000000002,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002681644342857143,
"min": 0.0002681644342857143,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037543020800000003,
"min": 0.0037543020800000003,
"max": 0.10393249359000002,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010622306726872921,
"min": 0.010622306726872921,
"max": 0.3014588952064514,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14871229231357574,
"min": 0.14871229231357574,
"max": 2.1102123260498047,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 417.4142857142857,
"min": 406.86301369863014,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29219.0,
"min": 15984.0,
"max": 33151.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4968542605638504,
"min": -1.0000000521540642,
"max": 1.5109177923774066,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 104.77979823946953,
"min": -31.999601677060127,
"max": 113.71059749275446,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4968542605638504,
"min": -1.0000000521540642,
"max": 1.5109177923774066,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 104.77979823946953,
"min": -31.999601677060127,
"max": 113.71059749275446,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.045984632000493415,
"min": 0.045984632000493415,
"max": 6.1178949093446136,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.2189242400345393,
"min": 3.2189242400345393,
"max": 97.88631854951382,
"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": "1676186948",
"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": "1676190207"
},
"total": 3259.17022232,
"count": 1,
"self": 0.5770983379998142,
"children": {
"run_training.setup": {
"total": 0.1349321070001679,
"count": 1,
"self": 0.1349321070001679
},
"TrainerController.start_learning": {
"total": 3258.458191875,
"count": 1,
"self": 2.1715712971199537,
"children": {
"TrainerController._reset_env": {
"total": 5.075671252000575,
"count": 1,
"self": 5.075671252000575
},
"TrainerController.advance": {
"total": 3251.1110652078787,
"count": 63510,
"self": 2.4302961088696975,
"children": {
"env_step": {
"total": 2071.9091472829496,
"count": 63510,
"self": 1935.9261510819779,
"children": {
"SubprocessEnvManager._take_step": {
"total": 134.59258717107514,
"count": 63510,
"self": 6.198530218134692,
"children": {
"TorchPolicy.evaluate": {
"total": 128.39405695294045,
"count": 62550,
"self": 27.46911733896286,
"children": {
"TorchPolicy.sample_actions": {
"total": 100.92493961397759,
"count": 62550,
"self": 100.92493961397759
}
}
}
}
},
"workers": {
"total": 1.3904090298965457,
"count": 63510,
"self": 0.0,
"children": {
"worker_root": {
"total": 3252.0993181087706,
"count": 63510,
"is_parallel": true,
"self": 1480.2412247839402,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0023218070000439184,
"count": 1,
"is_parallel": true,
"self": 0.0007942269994600792,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015275800005838391,
"count": 8,
"is_parallel": true,
"self": 0.0015275800005838391
}
}
},
"UnityEnvironment.step": {
"total": 0.13074793699979637,
"count": 1,
"is_parallel": true,
"self": 0.005732132000048296,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005825759999424918,
"count": 1,
"is_parallel": true,
"self": 0.0005825759999424918
},
"communicator.exchange": {
"total": 0.12229950599976291,
"count": 1,
"is_parallel": true,
"self": 0.12229950599976291
},
"steps_from_proto": {
"total": 0.0021337230000426644,
"count": 1,
"is_parallel": true,
"self": 0.00048295699798472924,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016507660020579351,
"count": 8,
"is_parallel": true,
"self": 0.0016507660020579351
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1771.8580933248304,
"count": 63509,
"is_parallel": true,
"self": 43.68030518779415,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.419065651000892,
"count": 63509,
"is_parallel": true,
"self": 25.419065651000892
},
"communicator.exchange": {
"total": 1561.1841916661951,
"count": 63509,
"is_parallel": true,
"self": 1561.1841916661951
},
"steps_from_proto": {
"total": 141.57453081984022,
"count": 63509,
"is_parallel": true,
"self": 32.25387829821739,
"children": {
"_process_rank_one_or_two_observation": {
"total": 109.32065252162283,
"count": 508072,
"is_parallel": true,
"self": 109.32065252162283
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1176.7716218160595,
"count": 63510,
"self": 4.1618329711773185,
"children": {
"process_trajectory": {
"total": 212.7761404168914,
"count": 63510,
"self": 212.53495677389128,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24118364300011308,
"count": 2,
"self": 0.24118364300011308
}
}
},
"_update_policy": {
"total": 959.8336484279907,
"count": 441,
"self": 274.6459500670644,
"children": {
"TorchPPOOptimizer.update": {
"total": 685.1876983609263,
"count": 22848,
"self": 685.1876983609263
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1850006558233872e-06,
"count": 1,
"self": 1.1850006558233872e-06
},
"TrainerController._save_models": {
"total": 0.09988293300011719,
"count": 1,
"self": 0.0037378839988377877,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0961450490012794,
"count": 1,
"self": 0.0961450490012794
}
}
}
}
}
}
}