Huggy-the-Puppo / run_logs /timers.json
DeathReaper0965's picture
learned puppo ppo agent push
22d13ac
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3477641344070435,
"min": 1.3477641344070435,
"max": 1.4271644353866577,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 67504.1171875,
"min": 66656.7109375,
"max": 78797.4375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 82.47078464106845,
"min": 75.74079754601227,
"max": 371.68148148148146,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49400.0,
"min": 48999.0,
"max": 50177.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999997.0,
"min": 49872.0,
"max": 1999997.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999997.0,
"min": 49872.0,
"max": 1999997.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4713692665100098,
"min": 0.1085435152053833,
"max": 2.5046255588531494,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1480.3502197265625,
"min": 14.544831275939941,
"max": 1585.098388671875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8931645334065457,
"min": 1.7072422876954079,
"max": 4.105898760422487,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2332.005555510521,
"min": 228.77046655118465,
"max": 2564.6871837973595,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8931645334065457,
"min": 1.7072422876954079,
"max": 4.105898760422487,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2332.005555510521,
"min": 228.77046655118465,
"max": 2564.6871837973595,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015262791563867117,
"min": 0.015037490063841688,
"max": 0.01912982018654778,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04578837469160135,
"min": 0.030074980127683375,
"max": 0.057389460559643335,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.045917419418692595,
"min": 0.021191489491611717,
"max": 0.04855267383158207,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1377522582560778,
"min": 0.042382978983223435,
"max": 0.1377522582560778,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4635488455166685e-06,
"min": 3.4635488455166685e-06,
"max": 0.000295376476541175,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0390646536550006e-05,
"min": 1.0390646536550006e-05,
"max": 0.0008440678686440499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115448333333332,
"min": 0.10115448333333332,
"max": 0.19845882500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30346344999999997,
"min": 0.20744010000000002,
"max": 0.58135595,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.760871833333336e-05,
"min": 6.760871833333336e-05,
"max": 0.0049230953675,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020282615500000008,
"min": 0.00020282615500000008,
"max": 0.014069661904999997,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1679890700",
"python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]",
"command_line_arguments": "/home/ppabolu/anaconda3/envs/deepRL/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy-the-Puppo --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": "1679896177"
},
"total": 5477.287377696484,
"count": 1,
"self": 0.4852929189801216,
"children": {
"run_training.setup": {
"total": 0.07678009197115898,
"count": 1,
"self": 0.07678009197115898
},
"TrainerController.start_learning": {
"total": 5476.725304685533,
"count": 1,
"self": 5.213195715099573,
"children": {
"TrainerController._reset_env": {
"total": 11.399732645601034,
"count": 1,
"self": 11.399732645601034
},
"TrainerController.advance": {
"total": 5459.585739143193,
"count": 232812,
"self": 5.387621909379959,
"children": {
"env_step": {
"total": 4695.1606619134545,
"count": 232812,
"self": 4323.76669523865,
"children": {
"SubprocessEnvManager._take_step": {
"total": 367.80504669994116,
"count": 232812,
"self": 19.786863684654236,
"children": {
"TorchPolicy.evaluate": {
"total": 348.0181830152869,
"count": 222948,
"self": 348.0181830152869
}
}
},
"workers": {
"total": 3.588919974863529,
"count": 232812,
"self": 0.0,
"children": {
"worker_root": {
"total": 5466.901013109833,
"count": 232812,
"is_parallel": true,
"self": 1464.959120310843,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010828077793121338,
"count": 1,
"is_parallel": true,
"self": 0.00031690672039985657,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007659010589122772,
"count": 2,
"is_parallel": true,
"self": 0.0007659010589122772
}
}
},
"UnityEnvironment.step": {
"total": 0.03627157211303711,
"count": 1,
"is_parallel": true,
"self": 0.00012057647109031677,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004039853811264038,
"count": 1,
"is_parallel": true,
"self": 0.0004039853811264038
},
"communicator.exchange": {
"total": 0.03511756658554077,
"count": 1,
"is_parallel": true,
"self": 0.03511756658554077
},
"steps_from_proto": {
"total": 0.0006294436752796173,
"count": 1,
"is_parallel": true,
"self": 0.00020921602845191956,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00042022764682769775,
"count": 2,
"is_parallel": true,
"self": 0.00042022764682769775
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 4001.94189279899,
"count": 232811,
"is_parallel": true,
"self": 22.541271444410086,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 297.64191883429885,
"count": 232811,
"is_parallel": true,
"self": 297.64191883429885
},
"communicator.exchange": {
"total": 3583.317511830479,
"count": 232811,
"is_parallel": true,
"self": 3583.317511830479
},
"steps_from_proto": {
"total": 98.44119068980217,
"count": 232811,
"is_parallel": true,
"self": 36.478584710508585,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.962605979293585,
"count": 465622,
"is_parallel": true,
"self": 61.962605979293585
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 759.0374553203583,
"count": 232812,
"self": 7.179403081536293,
"children": {
"process_trajectory": {
"total": 171.90152921900153,
"count": 232812,
"self": 167.230640091002,
"children": {
"RLTrainer._checkpoint": {
"total": 4.670889127999544,
"count": 10,
"self": 4.670889127999544
}
}
},
"_update_policy": {
"total": 579.9565230198205,
"count": 97,
"self": 498.98211320862174,
"children": {
"TorchPPOOptimizer.update": {
"total": 80.97440981119871,
"count": 4850,
"self": 80.97440981119871
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5944242477416992e-06,
"count": 1,
"self": 1.5944242477416992e-06
},
"TrainerController._save_models": {
"total": 0.5266355872154236,
"count": 1,
"self": 0.0705442950129509,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4560912922024727,
"count": 1,
"self": 0.4560912922024727
}
}
}
}
}
}
}