ppo-PyramidsRND / run_logs /timers.json
Nishant91's picture
First Push
5bb450c
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4252953827381134,
"min": 0.4252953827381134,
"max": 1.4778351783752441,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12677.205078125,
"min": 12677.205078125,
"max": 44831.609375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989946.0,
"min": 29952.0,
"max": 989946.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989946.0,
"min": 29952.0,
"max": 989946.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5929504036903381,
"min": -0.08187204599380493,
"max": 0.6296840310096741,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 168.39791870117188,
"min": -19.731163024902344,
"max": 178.83026123046875,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.05220938101410866,
"min": -0.05220938101410866,
"max": 0.2653592824935913,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -14.82746410369873,
"min": -14.82746410369873,
"max": 63.68622589111328,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06954198748309291,
"min": 0.06586564593651353,
"max": 0.0713004990372378,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9735878247633009,
"min": 0.4931245018786954,
"max": 1.0625097556136704,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015589070480306442,
"min": 0.0011480492256994374,
"max": 0.017647040732816664,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2182469867242902,
"min": 0.014924639934092687,
"max": 0.24705857025943329,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.303876136835714e-06,
"min": 7.303876136835714e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001022542659157,
"min": 0.0001022542659157,
"max": 0.0036327043890985997,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10243459285714286,
"min": 0.10243459285714286,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4340843,
"min": 1.3886848,
"max": 2.6109014000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002532158264285715,
"min": 0.0002532158264285715,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003545021570000001,
"min": 0.003545021570000001,
"max": 0.12110904986000003,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.0109663475304842,
"min": 0.010779505595564842,
"max": 0.39399123191833496,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1535288691520691,
"min": 0.1509130746126175,
"max": 2.7579386234283447,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 307.980198019802,
"min": 290.0693069306931,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31106.0,
"min": 15984.0,
"max": 32341.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6325940456573327,
"min": -1.0000000521540642,
"max": 1.6540978514450662,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 164.8919986113906,
"min": -29.881001688539982,
"max": 166.7001983076334,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6325940456573327,
"min": -1.0000000521540642,
"max": 1.6540978514450662,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 164.8919986113906,
"min": -29.881001688539982,
"max": 166.7001983076334,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03475909228878249,
"min": 0.0346278338909813,
"max": 8.300065194256604,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.5106683211670315,
"min": 3.255016385752242,
"max": 132.80104310810566,
"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": "1674324603",
"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": "1674326851"
},
"total": 2247.6625319190002,
"count": 1,
"self": 0.5390916430005745,
"children": {
"run_training.setup": {
"total": 0.0998102700000345,
"count": 1,
"self": 0.0998102700000345
},
"TrainerController.start_learning": {
"total": 2247.0236300059996,
"count": 1,
"self": 1.7287367689955317,
"children": {
"TrainerController._reset_env": {
"total": 6.195320562000234,
"count": 1,
"self": 6.195320562000234
},
"TrainerController.advance": {
"total": 2239.016740348004,
"count": 63861,
"self": 1.8149164299320546,
"children": {
"env_step": {
"total": 1562.765752423063,
"count": 63861,
"self": 1431.3727077260473,
"children": {
"SubprocessEnvManager._take_step": {
"total": 130.28524947697997,
"count": 63861,
"self": 5.193980057916178,
"children": {
"TorchPolicy.evaluate": {
"total": 125.09126941906379,
"count": 62547,
"self": 42.44381868213668,
"children": {
"TorchPolicy.sample_actions": {
"total": 82.64745073692711,
"count": 62547,
"self": 82.64745073692711
}
}
}
}
},
"workers": {
"total": 1.1077952200357686,
"count": 63861,
"self": 0.0,
"children": {
"worker_root": {
"total": 2241.345366150024,
"count": 63861,
"is_parallel": true,
"self": 931.7926572711021,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017237110000678513,
"count": 1,
"is_parallel": true,
"self": 0.0006243500001801294,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010993609998877218,
"count": 8,
"is_parallel": true,
"self": 0.0010993609998877218
}
}
},
"UnityEnvironment.step": {
"total": 0.045985892999851785,
"count": 1,
"is_parallel": true,
"self": 0.00046542899963242235,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004352920000201266,
"count": 1,
"is_parallel": true,
"self": 0.0004352920000201266
},
"communicator.exchange": {
"total": 0.04340032600021004,
"count": 1,
"is_parallel": true,
"self": 0.04340032600021004
},
"steps_from_proto": {
"total": 0.001684845999989193,
"count": 1,
"is_parallel": true,
"self": 0.00045770300039293943,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012271429995962535,
"count": 8,
"is_parallel": true,
"self": 0.0012271429995962535
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1309.5527088789217,
"count": 63860,
"is_parallel": true,
"self": 31.832620033892454,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.597115515953192,
"count": 63860,
"is_parallel": true,
"self": 24.597115515953192
},
"communicator.exchange": {
"total": 1140.9413434030316,
"count": 63860,
"is_parallel": true,
"self": 1140.9413434030316
},
"steps_from_proto": {
"total": 112.18162992604448,
"count": 63860,
"is_parallel": true,
"self": 26.028622831924167,
"children": {
"_process_rank_one_or_two_observation": {
"total": 86.15300709412031,
"count": 510880,
"is_parallel": true,
"self": 86.15300709412031
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 674.436071495009,
"count": 63861,
"self": 3.2454688489865475,
"children": {
"process_trajectory": {
"total": 156.2421050690309,
"count": 63861,
"self": 156.0563097060308,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18579536300012478,
"count": 2,
"self": 0.18579536300012478
}
}
},
"_update_policy": {
"total": 514.9484975769915,
"count": 451,
"self": 190.76645325003665,
"children": {
"TorchPPOOptimizer.update": {
"total": 324.18204432695484,
"count": 22827,
"self": 324.18204432695484
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0759995348053053e-06,
"count": 1,
"self": 1.0759995348053053e-06
},
"TrainerController._save_models": {
"total": 0.08283125100024336,
"count": 1,
"self": 0.0013422300007732701,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08148902099947009,
"count": 1,
"self": 0.08148902099947009
}
}
}
}
}
}
}