ppo-Huggy / run_logs /timers.json
MerlinTK's picture
feat: upload trained ppo-Huggy
ce22746
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4044249057769775,
"min": 1.4044249057769775,
"max": 1.4302395582199097,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68270.5,
"min": 68270.5,
"max": 76772.1875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 115.05069124423963,
"min": 86.67894736842105,
"max": 409.4146341463415,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49932.0,
"min": 49053.0,
"max": 50358.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999675.0,
"min": 49847.0,
"max": 1999675.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999675.0,
"min": 49847.0,
"max": 1999675.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.336772918701172,
"min": 0.07845016568899155,
"max": 2.4222800731658936,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1014.1594848632812,
"min": 9.57091999053955,
"max": 1357.99072265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5913003662489524,
"min": 1.9059883448921267,
"max": 3.9150099912889242,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1558.6243589520454,
"min": 232.53057807683945,
"max": 2117.029114305973,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5913003662489524,
"min": 1.9059883448921267,
"max": 3.9150099912889242,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1558.6243589520454,
"min": 232.53057807683945,
"max": 2117.029114305973,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017433310282326097,
"min": 0.013671728091624875,
"max": 0.019921023289215453,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05229993084697829,
"min": 0.028103962197201328,
"max": 0.05976306986764636,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04652393013238907,
"min": 0.02127096097295483,
"max": 0.06026067913820346,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.13957179039716722,
"min": 0.04254192194590966,
"max": 0.1748232459028562,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.193948935383342e-06,
"min": 3.193948935383342e-06,
"max": 0.00029535015154995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.581846806150026e-06,
"min": 9.581846806150026e-06,
"max": 0.00084409186863605,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1010646166666667,
"min": 0.1010646166666667,
"max": 0.19845005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3031938500000001,
"min": 0.20731765000000008,
"max": 0.5813639500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.312437166666682e-05,
"min": 6.312437166666682e-05,
"max": 0.004922657495000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018937311500000047,
"min": 0.00018937311500000047,
"max": 0.014070061105000004,
"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": "1676110821",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.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": "1676113203"
},
"total": 2381.209921462,
"count": 1,
"self": 0.3882397989996207,
"children": {
"run_training.setup": {
"total": 0.12267727699997977,
"count": 1,
"self": 0.12267727699997977
},
"TrainerController.start_learning": {
"total": 2380.699004386,
"count": 1,
"self": 4.321607176132602,
"children": {
"TrainerController._reset_env": {
"total": 10.539943406999896,
"count": 1,
"self": 10.539943406999896
},
"TrainerController.advance": {
"total": 2365.7197614338675,
"count": 231620,
"self": 4.429364596034702,
"children": {
"env_step": {
"total": 1842.695000615902,
"count": 231620,
"self": 1539.60117513888,
"children": {
"SubprocessEnvManager._take_step": {
"total": 300.39766449498916,
"count": 231620,
"self": 15.472965304007403,
"children": {
"TorchPolicy.evaluate": {
"total": 284.92469919098176,
"count": 222976,
"self": 70.83027211409285,
"children": {
"TorchPolicy.sample_actions": {
"total": 214.0944270768889,
"count": 222976,
"self": 214.0944270768889
}
}
}
}
},
"workers": {
"total": 2.6961609820327794,
"count": 231620,
"self": 0.0,
"children": {
"worker_root": {
"total": 2372.725371380978,
"count": 231620,
"is_parallel": true,
"self": 1116.7686706759075,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018353730000626456,
"count": 1,
"is_parallel": true,
"self": 0.0003499809999993886,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001485392000063257,
"count": 2,
"is_parallel": true,
"self": 0.001485392000063257
}
}
},
"UnityEnvironment.step": {
"total": 0.04559151899979952,
"count": 1,
"is_parallel": true,
"self": 0.000302024999882633,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002439249999497406,
"count": 1,
"is_parallel": true,
"self": 0.0002439249999497406
},
"communicator.exchange": {
"total": 0.04433022400007758,
"count": 1,
"is_parallel": true,
"self": 0.04433022400007758
},
"steps_from_proto": {
"total": 0.0007153449998895667,
"count": 1,
"is_parallel": true,
"self": 0.0002602389997719001,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00045510600011766655,
"count": 2,
"is_parallel": true,
"self": 0.00045510600011766655
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1255.9567007050703,
"count": 231619,
"is_parallel": true,
"self": 37.61602774605626,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.47729255389436,
"count": 231619,
"is_parallel": true,
"self": 79.47729255389436
},
"communicator.exchange": {
"total": 1043.3671881890657,
"count": 231619,
"is_parallel": true,
"self": 1043.3671881890657
},
"steps_from_proto": {
"total": 95.49619221605394,
"count": 231619,
"is_parallel": true,
"self": 37.48068152198243,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.01551069407151,
"count": 463238,
"is_parallel": true,
"self": 58.01551069407151
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 518.5953962219307,
"count": 231620,
"self": 6.710164343889346,
"children": {
"process_trajectory": {
"total": 159.74660581704416,
"count": 231620,
"self": 158.51890325404452,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2277025629996388,
"count": 10,
"self": 1.2277025629996388
}
}
},
"_update_policy": {
"total": 352.13862606099724,
"count": 97,
"self": 294.9476739570032,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.19095210399405,
"count": 2910,
"self": 57.19095210399405
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.069999578059651e-07,
"count": 1,
"self": 9.069999578059651e-07
},
"TrainerController._save_models": {
"total": 0.11769146200003888,
"count": 1,
"self": 0.002639807999912591,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11505165400012629,
"count": 1,
"self": 0.11505165400012629
}
}
}
}
}
}
}