Pengcheng-Wang's picture
First Push
27f8ec8 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3918796181678772,
"min": 0.3918796181678772,
"max": 1.46480393409729,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11725.0380859375,
"min": 11725.0380859375,
"max": 44436.29296875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989896.0,
"min": 29952.0,
"max": 989896.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989896.0,
"min": 29952.0,
"max": 989896.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4961211681365967,
"min": -0.08256803452968597,
"max": 0.500742495059967,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 136.929443359375,
"min": -19.898897171020508,
"max": 136.929443359375,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.027795670554041862,
"min": -0.005470703821629286,
"max": 0.5612117648124695,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.671605110168457,
"min": -1.4333244562149048,
"max": 133.00718688964844,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06982212243357924,
"min": 0.06445185204255995,
"max": 0.07303423169200653,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9775097140701094,
"min": 0.5097037957821994,
"max": 1.093180192480955,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015570792373376104,
"min": 0.0009230866168140102,
"max": 0.016423935074875818,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21799109322726545,
"min": 0.012923212635396142,
"max": 0.2463590261231373,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.603983179657146e-06,
"min": 7.603983179657146e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010645576451520004,
"min": 0.00010645576451520004,
"max": 0.0035092844302385996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253462857142859,
"min": 0.10253462857142859,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4354848000000002,
"min": 1.3886848,
"max": 2.5697614000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026320939428571446,
"min": 0.00026320939428571446,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036849315200000025,
"min": 0.0036849315200000025,
"max": 0.11699916386,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009358763694763184,
"min": 0.009358763694763184,
"max": 0.41709062457084656,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.13102269172668457,
"min": 0.13102269172668457,
"max": 2.9196343421936035,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 366.4404761904762,
"min": 366.4404761904762,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30781.0,
"min": 15984.0,
"max": 32626.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5357252730123967,
"min": -1.0000000521540642,
"max": 1.5709999792086773,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 127.46519766002893,
"min": -28.657001741230488,
"max": 127.46519766002893,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5357252730123967,
"min": -1.0000000521540642,
"max": 1.5709999792086773,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 127.46519766002893,
"min": -28.657001741230488,
"max": 127.46519766002893,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03543338614637986,
"min": 0.03543338614637986,
"max": 8.464977351948619,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.9409710501495283,
"min": 2.9409710501495283,
"max": 135.4396376311779,
"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": "1723158655",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1723162174"
},
"total": 3518.132767845,
"count": 1,
"self": 1.0501513010003691,
"children": {
"run_training.setup": {
"total": 0.07341907899990474,
"count": 1,
"self": 0.07341907899990474
},
"TrainerController.start_learning": {
"total": 3517.009197465,
"count": 1,
"self": 2.574642083933213,
"children": {
"TrainerController._reset_env": {
"total": 3.267353792999984,
"count": 1,
"self": 3.267353792999984
},
"TrainerController.advance": {
"total": 3511.0710651580666,
"count": 63776,
"self": 3.0281024180931126,
"children": {
"env_step": {
"total": 2320.3322677399956,
"count": 63776,
"self": 2136.425976039988,
"children": {
"SubprocessEnvManager._take_step": {
"total": 182.20889146907393,
"count": 63776,
"self": 8.210719333094858,
"children": {
"TorchPolicy.evaluate": {
"total": 173.99817213597908,
"count": 62566,
"self": 173.99817213597908
}
}
},
"workers": {
"total": 1.6974002309334537,
"count": 63776,
"self": 0.0,
"children": {
"worker_root": {
"total": 3509.0200176210237,
"count": 63776,
"is_parallel": true,
"self": 1585.067954078981,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003760972999771184,
"count": 1,
"is_parallel": true,
"self": 0.0012667979995057976,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002494175000265386,
"count": 8,
"is_parallel": true,
"self": 0.002494175000265386
}
}
},
"UnityEnvironment.step": {
"total": 0.07435939900005906,
"count": 1,
"is_parallel": true,
"self": 0.0009076180003830814,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0006391960000655672,
"count": 1,
"is_parallel": true,
"self": 0.0006391960000655672
},
"communicator.exchange": {
"total": 0.07048611099980917,
"count": 1,
"is_parallel": true,
"self": 0.07048611099980917
},
"steps_from_proto": {
"total": 0.0023264739998012374,
"count": 1,
"is_parallel": true,
"self": 0.0004790100006175635,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018474639991836739,
"count": 8,
"is_parallel": true,
"self": 0.0018474639991836739
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1923.9520635420427,
"count": 63775,
"is_parallel": true,
"self": 55.55347643091363,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 33.80837170504856,
"count": 63775,
"is_parallel": true,
"self": 33.80837170504856
},
"communicator.exchange": {
"total": 1694.435990897095,
"count": 63775,
"is_parallel": true,
"self": 1694.435990897095
},
"steps_from_proto": {
"total": 140.1542245089854,
"count": 63775,
"is_parallel": true,
"self": 31.4453133171055,
"children": {
"_process_rank_one_or_two_observation": {
"total": 108.7089111918799,
"count": 510200,
"is_parallel": true,
"self": 108.7089111918799
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1187.710694999978,
"count": 63776,
"self": 5.415724796860559,
"children": {
"process_trajectory": {
"total": 184.61546767810978,
"count": 63776,
"self": 184.37091925811,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24454841999977361,
"count": 2,
"self": 0.24454841999977361
}
}
},
"_update_policy": {
"total": 997.6795025250076,
"count": 455,
"self": 406.67477170501115,
"children": {
"TorchPPOOptimizer.update": {
"total": 591.0047308199964,
"count": 22800,
"self": 591.0047308199964
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1440006346674636e-06,
"count": 1,
"self": 1.1440006346674636e-06
},
"TrainerController._save_models": {
"total": 0.0961352859994804,
"count": 1,
"self": 0.0027411049995862413,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09339418099989416,
"count": 1,
"self": 0.09339418099989416
}
}
}
}
}
}
}