ppo-PyramidsRND / run_logs /timers.json
sigma-bit-dot's picture
First training of PyramidsRND
f967a4e
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.48090696334838867,
"min": 0.47415316104888916,
"max": 1.4089471101760864,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 14304.0966796875,
"min": 14209.421875,
"max": 42741.8203125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989960.0,
"min": 29997.0,
"max": 989960.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989960.0,
"min": 29997.0,
"max": 989960.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.33502399921417236,
"min": -0.08841744065284729,
"max": 0.33502399921417236,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 88.44633483886719,
"min": -21.308603286743164,
"max": 88.44633483886719,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.0029126342851668596,
"min": -0.0029126342851668596,
"max": 0.2387692779302597,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -0.7689354419708252,
"min": -0.7689354419708252,
"max": 57.54339599609375,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07078227396092132,
"min": 0.06393613333315434,
"max": 0.07252277228972183,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9909518354528984,
"min": 0.5685022081597655,
"max": 1.0428791837475728,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.010790094455243648,
"min": 0.00048229202199460524,
"max": 0.011640266591961799,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.15106132237341108,
"min": 0.006752088307924473,
"max": 0.1629637322874652,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.606404607421427e-06,
"min": 7.606404607421427e-06,
"max": 0.0002951598391133875,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010648966450389997,
"min": 0.00010648966450389997,
"max": 0.0036346312884563,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253543571428572,
"min": 0.10253543571428572,
"max": 0.1983866125,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4354961000000002,
"min": 1.4354961000000002,
"max": 2.6115437,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026329002785714287,
"min": 0.00026329002785714287,
"max": 0.00983882258875,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036860603900000003,
"min": 0.0036860603900000003,
"max": 0.12117321563000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00708233704790473,
"min": 0.00708233704790473,
"max": 0.3346102237701416,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.09915272146463394,
"min": 0.09915272146463394,
"max": 2.676881790161133,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 509.01666666666665,
"min": 498.25,
"max": 998.0645161290323,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30541.0,
"min": 16284.0,
"max": 33708.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.2242233044157425,
"min": -0.9341677927201794,
"max": 1.3231178379750677,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 73.45339826494455,
"min": -28.95920157432556,
"max": 74.0945989266038,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.2242233044157425,
"min": -0.9341677927201794,
"max": 1.3231178379750677,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 73.45339826494455,
"min": -28.95920157432556,
"max": 74.0945989266038,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.037232640438499706,
"min": 0.037232640438499706,
"max": 6.742127780528629,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.2339584263099823,
"min": 2.094044524303172,
"max": 114.6161722689867,
"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": "1702631102",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702633144"
},
"total": 2041.4727291069999,
"count": 1,
"self": 0.7527035319994866,
"children": {
"run_training.setup": {
"total": 0.0462765870001931,
"count": 1,
"self": 0.0462765870001931
},
"TrainerController.start_learning": {
"total": 2040.6737489880002,
"count": 1,
"self": 1.359396522028419,
"children": {
"TrainerController._reset_env": {
"total": 2.9681428090002555,
"count": 1,
"self": 2.9681428090002555
},
"TrainerController.advance": {
"total": 2036.2219169529722,
"count": 63455,
"self": 1.3388544550771257,
"children": {
"env_step": {
"total": 1398.9389075889221,
"count": 63455,
"self": 1273.0857780659858,
"children": {
"SubprocessEnvManager._take_step": {
"total": 125.06996112197749,
"count": 63455,
"self": 4.619782746961391,
"children": {
"TorchPolicy.evaluate": {
"total": 120.4501783750161,
"count": 62573,
"self": 120.4501783750161
}
}
},
"workers": {
"total": 0.7831684009588571,
"count": 63455,
"self": 0.0,
"children": {
"worker_root": {
"total": 2036.1095564699262,
"count": 63455,
"is_parallel": true,
"self": 876.1958325609817,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022762859998692875,
"count": 1,
"is_parallel": true,
"self": 0.000619281000126648,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016570049997426395,
"count": 8,
"is_parallel": true,
"self": 0.0016570049997426395
}
}
},
"UnityEnvironment.step": {
"total": 0.09206226900005277,
"count": 1,
"is_parallel": true,
"self": 0.0006066809996809752,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046977600004538544,
"count": 1,
"is_parallel": true,
"self": 0.00046977600004538544
},
"communicator.exchange": {
"total": 0.08921632500005217,
"count": 1,
"is_parallel": true,
"self": 0.08921632500005217
},
"steps_from_proto": {
"total": 0.001769487000274239,
"count": 1,
"is_parallel": true,
"self": 0.0003658559999166755,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014036310003575636,
"count": 8,
"is_parallel": true,
"self": 0.0014036310003575636
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1159.9137239089446,
"count": 63454,
"is_parallel": true,
"self": 34.63683967998168,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.360867810048603,
"count": 63454,
"is_parallel": true,
"self": 24.360867810048603
},
"communicator.exchange": {
"total": 1003.3090884699786,
"count": 63454,
"is_parallel": true,
"self": 1003.3090884699786
},
"steps_from_proto": {
"total": 97.60692794893566,
"count": 63454,
"is_parallel": true,
"self": 19.235124298060782,
"children": {
"_process_rank_one_or_two_observation": {
"total": 78.37180365087488,
"count": 507632,
"is_parallel": true,
"self": 78.37180365087488
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 635.9441549089729,
"count": 63455,
"self": 2.467751437995048,
"children": {
"process_trajectory": {
"total": 124.59183526997913,
"count": 63455,
"self": 124.36562862197889,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22620664800024315,
"count": 2,
"self": 0.22620664800024315
}
}
},
"_update_policy": {
"total": 508.88456820099873,
"count": 456,
"self": 304.1450605970181,
"children": {
"TorchPPOOptimizer.update": {
"total": 204.73950760398066,
"count": 22764,
"self": 204.73950760398066
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4019997252034955e-06,
"count": 1,
"self": 1.4019997252034955e-06
},
"TrainerController._save_models": {
"total": 0.12429130199961946,
"count": 1,
"self": 0.0020280869994167006,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12226321500020276,
"count": 1,
"self": 0.12226321500020276
}
}
}
}
}
}
}