ppo-PyramidsRND / run_logs /timers.json
andyleow's picture
First training of PyramidsRND
7445d98
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.34849366545677185,
"min": 0.337778776884079,
"max": 1.4804461002349854,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10443.658203125,
"min": 9992.84765625,
"max": 44910.8125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989914.0,
"min": 29952.0,
"max": 989914.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989914.0,
"min": 29952.0,
"max": 989914.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.568702757358551,
"min": -0.09134125709533691,
"max": 0.568702757358551,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 160.37417602539062,
"min": -22.104583740234375,
"max": 160.37417602539062,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.033062487840652466,
"min": -0.0009882235899567604,
"max": 0.3516363799571991,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 9.32362174987793,
"min": -0.2757143974304199,
"max": 83.33782196044922,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07141833584286493,
"min": 0.06463411743988261,
"max": 0.07319637919874204,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.999856701800109,
"min": 0.5123746543911943,
"max": 1.0597748787064725,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015446637013711228,
"min": 0.00017535252738435205,
"max": 0.015475156843811939,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2162529181919572,
"min": 0.0022795828559965766,
"max": 0.21665219581336714,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.468918938964288e-06,
"min": 7.468918938964288e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010456486514550004,
"min": 0.00010456486514550004,
"max": 0.0035083667305444996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10248960714285715,
"min": 0.10248960714285715,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4348545000000001,
"min": 1.3886848,
"max": 2.5694555000000006,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002587117535714287,
"min": 0.0002587117535714287,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003621964550000002,
"min": 0.003621964550000002,
"max": 0.11696860444999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00570130767300725,
"min": 0.0054936097003519535,
"max": 0.3308338522911072,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.07981830835342407,
"min": 0.07691053301095963,
"max": 2.3158369064331055,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 331.1333333333333,
"min": 331.1333333333333,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29802.0,
"min": 15984.0,
"max": 32319.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6485736113000702,
"min": -1.0000000521540642,
"max": 1.6485736113000702,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 150.0201986283064,
"min": -31.998401656746864,
"max": 150.0201986283064,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6485736113000702,
"min": -1.0000000521540642,
"max": 1.6485736113000702,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 150.0201986283064,
"min": -31.998401656746864,
"max": 150.0201986283064,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.019670031148672315,
"min": 0.019670031148672315,
"max": 7.170768063515425,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.7899728345291805,
"min": 1.7002073418698274,
"max": 114.7322890162468,
"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": "1681730016",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1681732164"
},
"total": 2148.0633081590004,
"count": 1,
"self": 0.43993393599976116,
"children": {
"run_training.setup": {
"total": 0.12577628300005017,
"count": 1,
"self": 0.12577628300005017
},
"TrainerController.start_learning": {
"total": 2147.4975979400006,
"count": 1,
"self": 1.3791652191839603,
"children": {
"TrainerController._reset_env": {
"total": 3.8371306300005017,
"count": 1,
"self": 3.8371306300005017
},
"TrainerController.advance": {
"total": 2142.191244251817,
"count": 63832,
"self": 1.3748287805119617,
"children": {
"env_step": {
"total": 1523.3418995392703,
"count": 63832,
"self": 1416.6938308122253,
"children": {
"SubprocessEnvManager._take_step": {
"total": 105.82461795620475,
"count": 63832,
"self": 4.611781513447568,
"children": {
"TorchPolicy.evaluate": {
"total": 101.21283644275718,
"count": 62575,
"self": 101.21283644275718
}
}
},
"workers": {
"total": 0.8234507708402816,
"count": 63832,
"self": 0.0,
"children": {
"worker_root": {
"total": 2142.5596982758234,
"count": 63832,
"is_parallel": true,
"self": 836.0507625041428,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019079240000792197,
"count": 1,
"is_parallel": true,
"self": 0.0005616770004053251,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013462469996738946,
"count": 8,
"is_parallel": true,
"self": 0.0013462469996738946
}
}
},
"UnityEnvironment.step": {
"total": 0.04843432899997424,
"count": 1,
"is_parallel": true,
"self": 0.0005233779993432108,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005061800002295058,
"count": 1,
"is_parallel": true,
"self": 0.0005061800002295058
},
"communicator.exchange": {
"total": 0.0458221010003399,
"count": 1,
"is_parallel": true,
"self": 0.0458221010003399
},
"steps_from_proto": {
"total": 0.0015826700000616256,
"count": 1,
"is_parallel": true,
"self": 0.00035668500095198397,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012259849991096416,
"count": 8,
"is_parallel": true,
"self": 0.0012259849991096416
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1306.5089357716806,
"count": 63831,
"is_parallel": true,
"self": 32.43653762872691,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.81569307398695,
"count": 63831,
"is_parallel": true,
"self": 22.81569307398695
},
"communicator.exchange": {
"total": 1157.6383712949773,
"count": 63831,
"is_parallel": true,
"self": 1157.6383712949773
},
"steps_from_proto": {
"total": 93.61833377398943,
"count": 63831,
"is_parallel": true,
"self": 19.9995268612538,
"children": {
"_process_rank_one_or_two_observation": {
"total": 73.61880691273564,
"count": 510648,
"is_parallel": true,
"self": 73.61880691273564
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 617.4745159320346,
"count": 63832,
"self": 2.505724434055992,
"children": {
"process_trajectory": {
"total": 103.85123301599197,
"count": 63832,
"self": 103.64978827099185,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2014447450001171,
"count": 2,
"self": 0.2014447450001171
}
}
},
"_update_policy": {
"total": 511.11755848198663,
"count": 447,
"self": 325.7324234870075,
"children": {
"TorchPPOOptimizer.update": {
"total": 185.38513499497913,
"count": 22833,
"self": 185.38513499497913
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0799994925037026e-06,
"count": 1,
"self": 1.0799994925037026e-06
},
"TrainerController._save_models": {
"total": 0.09005675899970811,
"count": 1,
"self": 0.0013508979991456727,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08870586100056244,
"count": 1,
"self": 0.08870586100056244
}
}
}
}
}
}
}