ppo-PyramidsRND / run_logs /timers.json
HilbertS's picture
first model
941b881
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.706527590751648,
"min": 0.706527590751648,
"max": 1.2970093488693237,
"count": 3
},
"Pyramids.Policy.Entropy.sum": {
"value": 21161.9140625,
"min": 21161.9140625,
"max": 39346.07421875,
"count": 3
},
"Pyramids.Step.mean": {
"value": 89951.0,
"min": 29952.0,
"max": 89951.0,
"count": 3
},
"Pyramids.Step.sum": {
"value": 89951.0,
"min": 29952.0,
"max": 89951.0,
"count": 3
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.1071084514260292,
"min": -0.1071084514260292,
"max": -0.05767878144979477,
"count": 3
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -25.70602798461914,
"min": -25.70602798461914,
"max": -13.66987133026123,
"count": 3
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.3648502230644226,
"min": 0.3648502230644226,
"max": 0.9536283016204834,
"count": 3
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 87.56405639648438,
"min": 87.56405639648438,
"max": 226.00990295410156,
"count": 3
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06870110483265894,
"min": 0.06870110483265894,
"max": 0.07356380360458682,
"count": 3
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.7557121531592483,
"min": 0.5149466252321078,
"max": 0.7615242658450441,
"count": 3
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.00038200626178225104,
"min": 0.00038200626178225104,
"max": 0.05783374607409495,
"count": 3
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.004202068879604761,
"min": 0.004202068879604761,
"max": 0.40483622251866463,
"count": 3
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.764089230154545e-05,
"min": 7.764089230154545e-05,
"max": 0.0002515063018788571,
"count": 3
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0008540498153169998,
"min": 0.0008540498153169998,
"max": 0.0018255574914810002,
"count": 3
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.12588027272727273,
"min": 0.12588027272727273,
"max": 0.1838354285714286,
"count": 3
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.384683,
"min": 1.2868480000000002,
"max": 1.7085190000000001,
"count": 3
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0025954392454545453,
"min": 0.0025954392454545453,
"max": 0.008385159314285713,
"count": 3
},
"Pyramids.Policy.Beta.sum": {
"value": 0.028549831699999997,
"min": 0.028549831699999997,
"max": 0.06090104810000001,
"count": 3
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.26381805539131165,
"min": 0.26381805539131165,
"max": 0.9614572525024414,
"count": 3
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 2.90199875831604,
"min": 2.90199875831604,
"max": 6.73020076751709,
"count": 3
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 999.0,
"min": 983.2121212121212,
"max": 999.0,
"count": 3
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31968.0,
"min": 15984.0,
"max": 32446.0,
"count": 3
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.9999375520274043,
"min": -1.0000000521540642,
"max": -0.8629091420408451,
"count": 3
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -31.998001664876938,
"min": -31.998001664876938,
"max": -16.000000834465027,
"count": 3
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.9999375520274043,
"min": -1.0000000521540642,
"max": -0.8629091420408451,
"count": 3
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -31.998001664876938,
"min": -31.998001664876938,
"max": -16.000000834465027,
"count": 3
},
"Pyramids.Policy.RndReward.mean": {
"value": 2.8148068226873875,
"min": 2.8148068226873875,
"max": 20.40450277365744,
"count": 3
},
"Pyramids.Policy.RndReward.sum": {
"value": 90.0738183259964,
"min": 90.0738183259964,
"max": 326.47204437851906,
"count": 3
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 3
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 3
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1683280336",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1683280534"
},
"total": 197.2664616720001,
"count": 1,
"self": 0.4742210869999326,
"children": {
"run_training.setup": {
"total": 0.042596888000161925,
"count": 1,
"self": 0.042596888000161925
},
"TrainerController.start_learning": {
"total": 196.749643697,
"count": 1,
"self": 0.12260912299257143,
"children": {
"TrainerController._reset_env": {
"total": 4.1899924659999215,
"count": 1,
"self": 4.1899924659999215
},
"TrainerController.advance": {
"total": 192.3272425750074,
"count": 6296,
"self": 0.1284703490332504,
"children": {
"env_step": {
"total": 126.6053709179912,
"count": 6296,
"self": 115.78977543397104,
"children": {
"SubprocessEnvManager._take_step": {
"total": 10.74045344901424,
"count": 6296,
"self": 0.4788389710490719,
"children": {
"TorchPolicy.evaluate": {
"total": 10.261614477965168,
"count": 6286,
"self": 10.261614477965168
}
}
},
"workers": {
"total": 0.07514203500591066,
"count": 6296,
"self": 0.0,
"children": {
"worker_root": {
"total": 196.2603720600132,
"count": 6296,
"is_parallel": true,
"self": 91.32423108199532,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019137389999741572,
"count": 1,
"is_parallel": true,
"self": 0.0005162609998023981,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001397478000171759,
"count": 8,
"is_parallel": true,
"self": 0.001397478000171759
}
}
},
"UnityEnvironment.step": {
"total": 0.0516912630000661,
"count": 1,
"is_parallel": true,
"self": 0.000577642000052947,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047463700002481346,
"count": 1,
"is_parallel": true,
"self": 0.00047463700002481346
},
"communicator.exchange": {
"total": 0.048769498999945426,
"count": 1,
"is_parallel": true,
"self": 0.048769498999945426
},
"steps_from_proto": {
"total": 0.0018694850000429142,
"count": 1,
"is_parallel": true,
"self": 0.0003984059997037548,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014710790003391594,
"count": 8,
"is_parallel": true,
"self": 0.0014710790003391594
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 104.93614097801787,
"count": 6295,
"is_parallel": true,
"self": 3.178952094014903,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.3218225900079688,
"count": 6295,
"is_parallel": true,
"self": 2.3218225900079688
},
"communicator.exchange": {
"total": 89.4434141060151,
"count": 6295,
"is_parallel": true,
"self": 89.4434141060151
},
"steps_from_proto": {
"total": 9.991952187979905,
"count": 6295,
"is_parallel": true,
"self": 2.002182516996072,
"children": {
"_process_rank_one_or_two_observation": {
"total": 7.989769670983833,
"count": 50360,
"is_parallel": true,
"self": 7.989769670983833
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 65.59340130798296,
"count": 6296,
"self": 0.1525017429851232,
"children": {
"process_trajectory": {
"total": 10.502626336999128,
"count": 6296,
"self": 10.502626336999128
},
"_update_policy": {
"total": 54.93827322799871,
"count": 33,
"self": 35.395548030981445,
"children": {
"TorchPPOOptimizer.update": {
"total": 19.542725197017262,
"count": 2280,
"self": 19.542725197017262
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.67000232776627e-07,
"count": 1,
"self": 9.67000232776627e-07
},
"TrainerController._save_models": {
"total": 0.10979856599988125,
"count": 1,
"self": 0.0014485199999398901,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10835004599994136,
"count": 1,
"self": 0.10835004599994136
}
}
}
}
}
}
}