ppo-PyramidsRND / run_logs /timers.json
saikiranp's picture
First training of PyramidsRND
668a19c
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.354724258184433,
"min": 0.354724258184433,
"max": 1.4311972856521606,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10607.673828125,
"min": 10607.673828125,
"max": 43416.80078125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989909.0,
"min": 29942.0,
"max": 989909.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989909.0,
"min": 29942.0,
"max": 989909.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3551175892353058,
"min": -0.1156456395983696,
"max": 0.4024066925048828,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 92.33057403564453,
"min": -27.754953384399414,
"max": 105.43054962158203,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.030001625418663025,
"min": 0.013187402859330177,
"max": 0.357007771730423,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.800422668457031,
"min": 3.4814743995666504,
"max": 84.61083984375,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06602441271598865,
"min": 0.06491788623717208,
"max": 0.07224542644852275,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9903661907398297,
"min": 0.5057179851396593,
"max": 1.038277832228535,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013510492222849278,
"min": 0.0002837238385301293,
"max": 0.016081601046261357,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.20265738334273917,
"min": 0.003688409900891681,
"max": 0.225142414647659,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.596837467753329e-06,
"min": 7.596837467753329e-06,
"max": 0.0002952333444460286,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011395256201629994,
"min": 0.00011395256201629994,
"max": 0.0036082053972648995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253224666666667,
"min": 0.10253224666666667,
"max": 0.19841111428571429,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5379837,
"min": 1.3888778,
"max": 2.5277187,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002629714419999999,
"min": 0.0002629714419999999,
"max": 0.009841270317142856,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003944571629999998,
"min": 0.003944571629999998,
"max": 0.12028323649000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.017204105854034424,
"min": 0.017204105854034424,
"max": 0.5529566407203674,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.25806158781051636,
"min": 0.24432560801506042,
"max": 3.870696544647217,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 510.1694915254237,
"min": 434.72463768115944,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30100.0,
"min": 16613.0,
"max": 32937.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.1887699672331413,
"min": -0.9999097292461703,
"max": 1.4830738237270942,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 71.32619803398848,
"min": -31.99640165269375,
"max": 96.39979854226112,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.1887699672331413,
"min": -0.9999097292461703,
"max": 1.4830738237270942,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 71.32619803398848,
"min": -31.99640165269375,
"max": 96.39979854226112,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.09074038836988621,
"min": 0.0801951661689099,
"max": 10.70980906661819,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 5.444423302193172,
"min": 5.183203927415889,
"max": 182.06675413250923,
"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": "1673452018",
"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": "1673454411"
},
"total": 2393.1668312819997,
"count": 1,
"self": 0.47755716700021367,
"children": {
"run_training.setup": {
"total": 0.11762555299992528,
"count": 1,
"self": 0.11762555299992528
},
"TrainerController.start_learning": {
"total": 2392.5716485619996,
"count": 1,
"self": 1.5854257429091376,
"children": {
"TrainerController._reset_env": {
"total": 6.8362330350000775,
"count": 1,
"self": 6.8362330350000775
},
"TrainerController.advance": {
"total": 2384.0418137450906,
"count": 63621,
"self": 1.616192863044489,
"children": {
"env_step": {
"total": 1661.473924934033,
"count": 63621,
"self": 1538.4197854910983,
"children": {
"SubprocessEnvManager._take_step": {
"total": 122.06969735695066,
"count": 63621,
"self": 5.009102428891538,
"children": {
"TorchPolicy.evaluate": {
"total": 117.06059492805912,
"count": 62564,
"self": 39.53905387709028,
"children": {
"TorchPolicy.sample_actions": {
"total": 77.52154105096884,
"count": 62564,
"self": 77.52154105096884
}
}
}
}
},
"workers": {
"total": 0.9844420859840284,
"count": 63621,
"self": 0.0,
"children": {
"worker_root": {
"total": 2387.6302787020186,
"count": 63621,
"is_parallel": true,
"self": 969.392527242966,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002011108000033346,
"count": 1,
"is_parallel": true,
"self": 0.0007641249999323918,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001246983000100954,
"count": 8,
"is_parallel": true,
"self": 0.001246983000100954
}
}
},
"UnityEnvironment.step": {
"total": 0.05306404899988593,
"count": 1,
"is_parallel": true,
"self": 0.0006155969999781519,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004808159999356576,
"count": 1,
"is_parallel": true,
"self": 0.0004808159999356576
},
"communicator.exchange": {
"total": 0.0501046409999617,
"count": 1,
"is_parallel": true,
"self": 0.0501046409999617
},
"steps_from_proto": {
"total": 0.0018629950000104145,
"count": 1,
"is_parallel": true,
"self": 0.0004884800002855627,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013745149997248518,
"count": 8,
"is_parallel": true,
"self": 0.0013745149997248518
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1418.2377514590526,
"count": 63620,
"is_parallel": true,
"self": 31.6984673098882,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 27.314615026037245,
"count": 63620,
"is_parallel": true,
"self": 27.314615026037245
},
"communicator.exchange": {
"total": 1247.6935183621076,
"count": 63620,
"is_parallel": true,
"self": 1247.6935183621076
},
"steps_from_proto": {
"total": 111.53115076101949,
"count": 63620,
"is_parallel": true,
"self": 26.628848834943028,
"children": {
"_process_rank_one_or_two_observation": {
"total": 84.90230192607646,
"count": 508960,
"is_parallel": true,
"self": 84.90230192607646
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 720.9516959480134,
"count": 63621,
"self": 2.9347500919830054,
"children": {
"process_trajectory": {
"total": 164.10474770702876,
"count": 63621,
"self": 163.83715446802898,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2675932389997797,
"count": 2,
"self": 0.2675932389997797
}
}
},
"_update_policy": {
"total": 553.9121981490016,
"count": 457,
"self": 216.4857368529856,
"children": {
"TorchPPOOptimizer.update": {
"total": 337.426461296016,
"count": 22833,
"self": 337.426461296016
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.436999809811823e-06,
"count": 1,
"self": 1.436999809811823e-06
},
"TrainerController._save_models": {
"total": 0.10817460199996276,
"count": 1,
"self": 0.0016312939997078502,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10654330800025491,
"count": 1,
"self": 0.10654330800025491
}
}
}
}
}
}
}