ppo-Huggy / run_logs /timers.json
hossniper's picture
Huggy
350fa1b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4105719327926636,
"min": 1.4105719327926636,
"max": 1.427746295928955,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68373.2421875,
"min": 68373.2421875,
"max": 77741.40625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.47920433996383,
"min": 74.77121212121212,
"max": 387.3076923076923,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49482.0,
"min": 48812.0,
"max": 50350.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999965.0,
"min": 49730.0,
"max": 1999965.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999965.0,
"min": 49730.0,
"max": 1999965.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.469085454940796,
"min": 0.04463466256856918,
"max": 2.5040063858032227,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1365.404296875,
"min": 5.757871627807617,
"max": 1631.90966796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7795357823803024,
"min": 1.7101872995380283,
"max": 4.044487839465202,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2090.083287656307,
"min": 220.61416164040565,
"max": 2566.813168466091,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7795357823803024,
"min": 1.7101872995380283,
"max": 4.044487839465202,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2090.083287656307,
"min": 220.61416164040565,
"max": 2566.813168466091,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0164690728068106,
"min": 0.012040833951141394,
"max": 0.02084096818968343,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.049407218420431796,
"min": 0.024081667902282788,
"max": 0.057718234289010684,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05432417694893149,
"min": 0.023402411863207816,
"max": 0.06460938608894745,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16297253084679447,
"min": 0.04680482372641563,
"max": 0.1894748336325089,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.572448809216669e-06,
"min": 3.572448809216669e-06,
"max": 0.0002952993015669,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0717346427650007e-05,
"min": 1.0717346427650007e-05,
"max": 0.0008439850686716499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10119078333333331,
"min": 0.10119078333333331,
"max": 0.1984331,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30357234999999994,
"min": 0.20751749999999997,
"max": 0.5813283500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.942008833333337e-05,
"min": 6.942008833333337e-05,
"max": 0.00492181169,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020826026500000012,
"min": 0.00020826026500000012,
"max": 0.014068284665,
"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": "1713931716",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1713934169"
},
"total": 2453.163509308,
"count": 1,
"self": 0.44028457099966545,
"children": {
"run_training.setup": {
"total": 0.05835201400009282,
"count": 1,
"self": 0.05835201400009282
},
"TrainerController.start_learning": {
"total": 2452.6648727230004,
"count": 1,
"self": 4.499577648823106,
"children": {
"TrainerController._reset_env": {
"total": 3.0743834460001835,
"count": 1,
"self": 3.0743834460001835
},
"TrainerController.advance": {
"total": 2444.979284980177,
"count": 233201,
"self": 4.828088264162034,
"children": {
"env_step": {
"total": 1958.2379503690038,
"count": 233201,
"self": 1629.415292850828,
"children": {
"SubprocessEnvManager._take_step": {
"total": 325.92825323703346,
"count": 233201,
"self": 17.504934541025023,
"children": {
"TorchPolicy.evaluate": {
"total": 308.42331869600844,
"count": 222920,
"self": 308.42331869600844
}
}
},
"workers": {
"total": 2.894404281142215,
"count": 233201,
"self": 0.0,
"children": {
"worker_root": {
"total": 2445.4909030880704,
"count": 233201,
"is_parallel": true,
"self": 1126.9368243449208,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010234760000003007,
"count": 1,
"is_parallel": true,
"self": 0.00023541800010207226,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007880579998982284,
"count": 2,
"is_parallel": true,
"self": 0.0007880579998982284
}
}
},
"UnityEnvironment.step": {
"total": 0.029851280999992014,
"count": 1,
"is_parallel": true,
"self": 0.0003684350001549319,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020637699981307378,
"count": 1,
"is_parallel": true,
"self": 0.00020637699981307378
},
"communicator.exchange": {
"total": 0.028517067000166207,
"count": 1,
"is_parallel": true,
"self": 0.028517067000166207
},
"steps_from_proto": {
"total": 0.0007594019998578005,
"count": 1,
"is_parallel": true,
"self": 0.00019886399968527257,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000560538000172528,
"count": 2,
"is_parallel": true,
"self": 0.000560538000172528
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1318.5540787431496,
"count": 233200,
"is_parallel": true,
"self": 39.85161435223972,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.15091002290183,
"count": 233200,
"is_parallel": true,
"self": 83.15091002290183
},
"communicator.exchange": {
"total": 1102.0491969160237,
"count": 233200,
"is_parallel": true,
"self": 1102.0491969160237
},
"steps_from_proto": {
"total": 93.50235745198438,
"count": 233200,
"is_parallel": true,
"self": 33.41997425793329,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.08238319405109,
"count": 466400,
"is_parallel": true,
"self": 60.08238319405109
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 481.9132463470114,
"count": 233201,
"self": 6.595466595992548,
"children": {
"process_trajectory": {
"total": 162.60205109801996,
"count": 233201,
"self": 161.2724172880196,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3296338100003595,
"count": 10,
"self": 1.3296338100003595
}
}
},
"_update_policy": {
"total": 312.7157286529989,
"count": 97,
"self": 251.14248803799546,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.57324061500344,
"count": 2910,
"self": 61.57324061500344
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.500001058564521e-07,
"count": 1,
"self": 8.500001058564521e-07
},
"TrainerController._save_models": {
"total": 0.11162579800020467,
"count": 1,
"self": 0.001991535000342992,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10963426299986168,
"count": 1,
"self": 0.10963426299986168
}
}
}
}
}
}
}