ppo-PyramidsRND / run_logs /timers.json
AbdelKarim95's picture
Push to Hub
d1cf676
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.578961968421936,
"min": 0.5519139766693115,
"max": 1.4427200555801392,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 17424.439453125,
"min": 16557.419921875,
"max": 43766.35546875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989972.0,
"min": 29952.0,
"max": 989972.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989972.0,
"min": 29952.0,
"max": 989972.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.04317491501569748,
"min": -0.16718034446239471,
"max": 0.04901187866926193,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 10.793728828430176,
"min": -39.621742248535156,
"max": 12.252969741821289,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.004607563838362694,
"min": 0.00037137544131837785,
"max": 0.22766853868961334,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.1518909931182861,
"min": 0.09024423360824585,
"max": 53.95744323730469,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06749108149753218,
"min": 0.06444515864971663,
"max": 0.07373112722766959,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9448751409654506,
"min": 0.5066051211951759,
"max": 1.057826991496019,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.004679501191465838,
"min": 0.0003199926372955844,
"max": 0.006452980737213648,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.06551301668052173,
"min": 0.0035199190102514284,
"max": 0.09034173032099108,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.578140331128569e-06,
"min": 7.578140331128569e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010609396463579996,
"min": 0.00010609396463579996,
"max": 0.0032529962156679997,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10252601428571428,
"min": 0.10252601428571428,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4353642,
"min": 1.3886848,
"max": 2.5275072,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002623488271428571,
"min": 0.0002623488271428571,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036728835799999995,
"min": 0.0036728835799999995,
"max": 0.10845476679999998,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.014657237567007542,
"min": 0.014657237567007542,
"max": 0.5563263297080994,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.20520132780075073,
"min": 0.20520132780075073,
"max": 3.894284248352051,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 802.1578947368421,
"min": 747.6,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30482.0,
"min": 15984.0,
"max": 33634.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.26947688292234373,
"min": -1.0000000521540642,
"max": 0.42137557304486994,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 10.509598433971405,
"min": -31.998801663517952,
"max": 17.27639849483967,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.26947688292234373,
"min": -1.0000000521540642,
"max": 0.42137557304486994,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 10.509598433971405,
"min": -31.998801663517952,
"max": 17.27639849483967,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.12176323886692095,
"min": 0.11573479615617543,
"max": 11.171646252274513,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.748766315809917,
"min": 4.46357443195302,
"max": 178.7463400363922,
"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": "1695212309",
"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": "1695214612"
},
"total": 2302.981994324,
"count": 1,
"self": 0.48170306100018934,
"children": {
"run_training.setup": {
"total": 0.046133998999948744,
"count": 1,
"self": 0.046133998999948744
},
"TrainerController.start_learning": {
"total": 2302.454157264,
"count": 1,
"self": 1.610595293982442,
"children": {
"TrainerController._reset_env": {
"total": 4.05818593999993,
"count": 1,
"self": 4.05818593999993
},
"TrainerController.advance": {
"total": 2296.683655789018,
"count": 63316,
"self": 1.683377330994972,
"children": {
"env_step": {
"total": 1603.5634925810016,
"count": 63316,
"self": 1479.1161953839458,
"children": {
"SubprocessEnvManager._take_step": {
"total": 123.4577215130189,
"count": 63316,
"self": 5.349949221979159,
"children": {
"TorchPolicy.evaluate": {
"total": 118.10777229103974,
"count": 62564,
"self": 118.10777229103974
}
}
},
"workers": {
"total": 0.9895756840369359,
"count": 63316,
"self": 0.0,
"children": {
"worker_root": {
"total": 2296.135980292916,
"count": 63316,
"is_parallel": true,
"self": 944.7737477848816,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019146350000482926,
"count": 1,
"is_parallel": true,
"self": 0.0005757760000051348,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013388590000431577,
"count": 8,
"is_parallel": true,
"self": 0.0013388590000431577
}
}
},
"UnityEnvironment.step": {
"total": 0.057489896000106455,
"count": 1,
"is_parallel": true,
"self": 0.0006751990001703234,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000557353999965926,
"count": 1,
"is_parallel": true,
"self": 0.000557353999965926
},
"communicator.exchange": {
"total": 0.05288578599993343,
"count": 1,
"is_parallel": true,
"self": 0.05288578599993343
},
"steps_from_proto": {
"total": 0.0033715570000367734,
"count": 1,
"is_parallel": true,
"self": 0.0005101749995901628,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0028613820004466106,
"count": 8,
"is_parallel": true,
"self": 0.0028613820004466106
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1351.3622325080344,
"count": 63315,
"is_parallel": true,
"self": 35.430201727970825,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.3887886340392,
"count": 63315,
"is_parallel": true,
"self": 25.3887886340392
},
"communicator.exchange": {
"total": 1175.474511279014,
"count": 63315,
"is_parallel": true,
"self": 1175.474511279014
},
"steps_from_proto": {
"total": 115.06873086701034,
"count": 63315,
"is_parallel": true,
"self": 23.29111319532035,
"children": {
"_process_rank_one_or_two_observation": {
"total": 91.77761767169,
"count": 506520,
"is_parallel": true,
"self": 91.77761767169
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 691.4367858770215,
"count": 63316,
"self": 2.970973693009455,
"children": {
"process_trajectory": {
"total": 121.05585074601527,
"count": 63316,
"self": 120.84179703701534,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21405370899992704,
"count": 2,
"self": 0.21405370899992704
}
}
},
"_update_policy": {
"total": 567.4099614379968,
"count": 447,
"self": 371.2164250279757,
"children": {
"TorchPPOOptimizer.update": {
"total": 196.19353641002112,
"count": 22779,
"self": 196.19353641002112
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.027000052999938e-06,
"count": 1,
"self": 1.027000052999938e-06
},
"TrainerController._save_models": {
"total": 0.101719213999786,
"count": 1,
"self": 0.0014165949996822746,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10030261900010373,
"count": 1,
"self": 0.10030261900010373
}
}
}
}
}
}
}