ppo-Huggy / run_logs /timers.json
MrNoOne's picture
Huggy initial commit
b1815f6
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4072006940841675,
"min": 1.407192349433899,
"max": 1.4291712045669556,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69443.9453125,
"min": 68817.625,
"max": 78449.15625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 107.24458874458874,
"min": 86.23734729493891,
"max": 419.4583333333333,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49547.0,
"min": 49002.0,
"max": 50335.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999989.0,
"min": 49744.0,
"max": 1999989.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999989.0,
"min": 49744.0,
"max": 1999989.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3480143547058105,
"min": 0.09208399057388306,
"max": 2.416306734085083,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1084.7825927734375,
"min": 10.95799446105957,
"max": 1347.7100830078125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6200029141717143,
"min": 1.7347185813328798,
"max": 3.988636634163697,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1672.441346347332,
"min": 206.4315111786127,
"max": 2145.886509180069,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6200029141717143,
"min": 1.7347185813328798,
"max": 3.988636634163697,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1672.441346347332,
"min": 206.4315111786127,
"max": 2145.886509180069,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01738018190986218,
"min": 0.013181823798610518,
"max": 0.019924431427433675,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05214054572958654,
"min": 0.026363647597221037,
"max": 0.05977329428230102,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.045880854957633554,
"min": 0.021436336326102416,
"max": 0.05775340236723423,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.13764256487290066,
"min": 0.04287267265220483,
"max": 0.16935638425250849,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.0894989702000096e-06,
"min": 3.0894989702000096e-06,
"max": 0.00029530777656407495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.268496910600029e-06,
"min": 9.268496910600029e-06,
"max": 0.0008439375186875,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10102979999999999,
"min": 0.10102979999999999,
"max": 0.198435925,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30308939999999995,
"min": 0.2072472500000001,
"max": 0.5813125000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.138702000000016e-05,
"min": 6.138702000000016e-05,
"max": 0.004921952657499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018416106000000048,
"min": 0.00018416106000000048,
"max": 0.014067493749999998,
"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": "1684825687",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1684828053"
},
"total": 2366.051970331,
"count": 1,
"self": 0.4398536140001852,
"children": {
"run_training.setup": {
"total": 0.04802689799998916,
"count": 1,
"self": 0.04802689799998916
},
"TrainerController.start_learning": {
"total": 2365.564089819,
"count": 1,
"self": 4.431897445068444,
"children": {
"TrainerController._reset_env": {
"total": 4.32209893400011,
"count": 1,
"self": 4.32209893400011
},
"TrainerController.advance": {
"total": 2356.6992819519314,
"count": 231795,
"self": 4.390827634885227,
"children": {
"env_step": {
"total": 1834.295046726081,
"count": 231795,
"self": 1550.1941471250116,
"children": {
"SubprocessEnvManager._take_step": {
"total": 281.32701491403293,
"count": 231795,
"self": 16.704872034023765,
"children": {
"TorchPolicy.evaluate": {
"total": 264.62214288000916,
"count": 222956,
"self": 264.62214288000916
}
}
},
"workers": {
"total": 2.7738846870365705,
"count": 231795,
"self": 0.0,
"children": {
"worker_root": {
"total": 2357.972396382014,
"count": 231795,
"is_parallel": true,
"self": 1092.8893322969948,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009105719999524808,
"count": 1,
"is_parallel": true,
"self": 0.00028447199986203486,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000626100000090446,
"count": 2,
"is_parallel": true,
"self": 0.000626100000090446
}
}
},
"UnityEnvironment.step": {
"total": 0.06871449799996299,
"count": 1,
"is_parallel": true,
"self": 0.00034105599979739054,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002532230000724667,
"count": 1,
"is_parallel": true,
"self": 0.0002532230000724667
},
"communicator.exchange": {
"total": 0.0673459270000194,
"count": 1,
"is_parallel": true,
"self": 0.0673459270000194
},
"steps_from_proto": {
"total": 0.0007742920000737286,
"count": 1,
"is_parallel": true,
"self": 0.00022441500004788395,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005498770000258446,
"count": 2,
"is_parallel": true,
"self": 0.0005498770000258446
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1265.083064085019,
"count": 231794,
"is_parallel": true,
"self": 38.51130154910879,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.278390912904,
"count": 231794,
"is_parallel": true,
"self": 78.278390912904
},
"communicator.exchange": {
"total": 1055.9516315790197,
"count": 231794,
"is_parallel": true,
"self": 1055.9516315790197
},
"steps_from_proto": {
"total": 92.34174004398653,
"count": 231794,
"is_parallel": true,
"self": 33.55204638302246,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.789693660964076,
"count": 463588,
"is_parallel": true,
"self": 58.789693660964076
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 518.0134075909651,
"count": 231795,
"self": 6.438547195074307,
"children": {
"process_trajectory": {
"total": 132.07867016988996,
"count": 231795,
"self": 130.65205651588974,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4266136540002208,
"count": 10,
"self": 1.4266136540002208
}
}
},
"_update_policy": {
"total": 379.49619022600086,
"count": 97,
"self": 320.15659728899993,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.33959293700093,
"count": 2910,
"self": 59.33959293700093
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.149998732027598e-07,
"count": 1,
"self": 9.149998732027598e-07
},
"TrainerController._save_models": {
"total": 0.11081057299998065,
"count": 1,
"self": 0.0019436180000411696,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10886695499993948,
"count": 1,
"self": 0.10886695499993948
}
}
}
}
}
}
}