ppo-Pyramids / run_logs /timers.json
bitcloud2's picture
Upload trained ppo angent
1384882
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.29632407426834106,
"min": 0.29632407426834106,
"max": 1.5403083562850952,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 8927.6513671875,
"min": 8927.6513671875,
"max": 46726.79296875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989903.0,
"min": 29952.0,
"max": 989903.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989903.0,
"min": 29952.0,
"max": 989903.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7151656150817871,
"min": -0.09618700295686722,
"max": 0.7378317713737488,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 206.682861328125,
"min": -23.084880828857422,
"max": 213.97122192382812,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.008746386505663395,
"min": -0.009640068747103214,
"max": 0.0665053054690361,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.527705669403076,
"min": -2.699219226837158,
"max": 15.961274147033691,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.1410652368106366,
"min": 0.1334677934350009,
"max": 0.14329725821312161,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.9749133153489125,
"min": 0.97487571929361,
"max": 2.1007529538136787,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014316980798867741,
"min": 0.00015587703832115242,
"max": 0.016926021600349717,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.20043773118414837,
"min": 0.0012470163065692193,
"max": 0.25389032400524575,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.480490363678572e-06,
"min": 7.480490363678572e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010472686509150001,
"min": 0.00010472686509150001,
"max": 0.0032173567275479,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249346428571429,
"min": 0.10249346428571429,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4349085000000001,
"min": 1.3691136000000002,
"max": 2.5724521,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025909708214285726,
"min": 0.00025909708214285726,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036273591500000013,
"min": 0.0036273591500000013,
"max": 0.10728796479000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.005761183798313141,
"min": 0.005750850774347782,
"max": 0.15230296552181244,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.08065657317638397,
"min": 0.0805119127035141,
"max": 1.0661207437515259,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 265.76851851851853,
"min": 251.58823529411765,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28703.0,
"min": 15984.0,
"max": 33657.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.698075211786349,
"min": -1.0000000521540642,
"max": 1.7315999885567097,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 185.09019808471203,
"min": -32.000001668930054,
"max": 206.06039863824844,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.698075211786349,
"min": -1.0000000521540642,
"max": 1.7315999885567097,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 185.09019808471203,
"min": -32.000001668930054,
"max": 206.06039863824844,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.016119487592715497,
"min": 0.015575960488229826,
"max": 5.2803085970226675,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.7570241476059891,
"min": 1.7570241476059891,
"max": 84.48493755236268,
"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": "1673396214",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1673399210"
},
"total": 2995.4692560729995,
"count": 1,
"self": 0.4753100689990788,
"children": {
"run_training.setup": {
"total": 0.11263990500015097,
"count": 1,
"self": 0.11263990500015097
},
"TrainerController.start_learning": {
"total": 2994.881306099,
"count": 1,
"self": 1.3986297379492498,
"children": {
"TrainerController._reset_env": {
"total": 6.673080802999948,
"count": 1,
"self": 6.673080802999948
},
"TrainerController.advance": {
"total": 2986.7116021560505,
"count": 64194,
"self": 1.5280663121120597,
"children": {
"env_step": {
"total": 1602.191850695971,
"count": 64194,
"self": 1483.466479117912,
"children": {
"SubprocessEnvManager._take_step": {
"total": 117.81589539908396,
"count": 64194,
"self": 4.853992770101513,
"children": {
"TorchPolicy.evaluate": {
"total": 112.96190262898244,
"count": 62558,
"self": 37.90350348005177,
"children": {
"TorchPolicy.sample_actions": {
"total": 75.05839914893068,
"count": 62558,
"self": 75.05839914893068
}
}
}
}
},
"workers": {
"total": 0.9094761789749555,
"count": 64194,
"self": 0.0,
"children": {
"worker_root": {
"total": 2989.5609192799393,
"count": 64194,
"is_parallel": true,
"self": 1619.6630636859504,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0029653289998350374,
"count": 1,
"is_parallel": true,
"self": 0.0010513249997075036,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019140040001275338,
"count": 8,
"is_parallel": true,
"self": 0.0019140040001275338
}
}
},
"UnityEnvironment.step": {
"total": 0.04896679600005882,
"count": 1,
"is_parallel": true,
"self": 0.0005579050000505958,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005537760000606795,
"count": 1,
"is_parallel": true,
"self": 0.0005537760000606795
},
"communicator.exchange": {
"total": 0.04595354299999599,
"count": 1,
"is_parallel": true,
"self": 0.04595354299999599
},
"steps_from_proto": {
"total": 0.0019015719999515568,
"count": 1,
"is_parallel": true,
"self": 0.0004566960001284315,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014448759998231253,
"count": 8,
"is_parallel": true,
"self": 0.0014448759998231253
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1369.8978555939889,
"count": 64193,
"is_parallel": true,
"self": 30.653625318995864,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 26.061468696990232,
"count": 64193,
"is_parallel": true,
"self": 26.061468696990232
},
"communicator.exchange": {
"total": 1206.2104618829999,
"count": 64193,
"is_parallel": true,
"self": 1206.2104618829999
},
"steps_from_proto": {
"total": 106.9722996950029,
"count": 64193,
"is_parallel": true,
"self": 25.765022355232986,
"children": {
"_process_rank_one_or_two_observation": {
"total": 81.20727733976992,
"count": 513544,
"is_parallel": true,
"self": 81.20727733976992
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1382.9916851479675,
"count": 64194,
"self": 2.5328275140989263,
"children": {
"process_trajectory": {
"total": 165.70760912186847,
"count": 64194,
"self": 165.37805109086844,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3295580310000332,
"count": 2,
"self": 0.3295580310000332
}
}
},
"_update_policy": {
"total": 1214.751248512,
"count": 439,
"self": 219.7225845429639,
"children": {
"TorchPPOOptimizer.update": {
"total": 995.0286639690362,
"count": 93120,
"self": 995.0286639690362
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.007000719255302e-06,
"count": 1,
"self": 1.007000719255302e-06
},
"TrainerController._save_models": {
"total": 0.09799239499989199,
"count": 1,
"self": 0.0013808610001433408,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09661153399974864,
"count": 1,
"self": 0.09661153399974864
}
}
}
}
}
}
}