ppo-Huggy / run_logs /timers.json
CamposCaio's picture
Huggy
287ec72
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4522162675857544,
"min": 1.418938398361206,
"max": 1.4561901092529297,
"count": 500
},
"Huggy.Policy.Entropy.sum": {
"value": 15965.666015625,
"min": 12045.5615234375,
"max": 18410.7265625,
"count": 500
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 107.45360824742268,
"min": 72.18382352941177,
"max": 465.6666666666667,
"count": 500
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 10423.0,
"min": 7848.0,
"max": 12033.0,
"count": 500
},
"Huggy.Step.mean": {
"value": 4999921.0,
"min": 9868.0,
"max": 4999921.0,
"count": 500
},
"Huggy.Step.sum": {
"value": 4999921.0,
"min": 9868.0,
"max": 4999921.0,
"count": 500
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 3.104992151260376,
"min": 5.0667320465436205e-05,
"max": 3.1660592555999756,
"count": 500
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 316.7091979980469,
"min": 0.0014693522825837135,
"max": 410.5024719238281,
"count": 500
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6693236772547064,
"min": 1.4030788029943193,
"max": 4.260715696390937,
"count": 500
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 355.9243966937065,
"min": 27.72333413362503,
"max": 505.6282682418823,
"count": 500
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 5.503985489766622,
"min": 2.10461823535817,
"max": 6.391073577544269,
"count": 500
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 533.8865925073624,
"min": 41.585001826286316,
"max": 758.4424010515213,
"count": 500
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 500
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 500
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.00918747693678597,
"min": 0.008298434922544402,
"max": 0.014922066464205273,
"count": 121
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.00918747693678597,
"min": 0.008298434922544402,
"max": 0.014922066464205273,
"count": 121
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.11819348633289337,
"min": 0.07947969973087311,
"max": 0.19333260327577592,
"count": 121
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.11819348633289337,
"min": 0.07947969973087311,
"max": 0.19333260327577592,
"count": 121
},
"Huggy.Policy.LearningRate.mean": {
"value": 6.28199371899998e-07,
"min": 6.28199371899998e-07,
"max": 9.917694082306e-05,
"count": 121
},
"Huggy.Policy.LearningRate.sum": {
"value": 6.28199371899998e-07,
"min": 6.28199371899998e-07,
"max": 9.917694082306e-05,
"count": 121
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.09999999999999998,
"min": 0.09999999999999998,
"max": 0.09999999999999998,
"count": 121
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.09999999999999998,
"min": 0.09999999999999998,
"max": 0.09999999999999998,
"count": 121
},
"Huggy.Policy.Beta.mean": {
"value": 7.274718999999981e-05,
"min": 7.274718999999981e-05,
"max": 0.009917776306,
"count": 121
},
"Huggy.Policy.Beta.sum": {
"value": 7.274718999999981e-05,
"min": 7.274718999999981e-05,
"max": 0.009917776306,
"count": 121
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1688286650",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1688293970"
},
"total": 7320.160826024,
"count": 1,
"self": 0.8624480549997315,
"children": {
"run_training.setup": {
"total": 0.0424793279998994,
"count": 1,
"self": 0.0424793279998994
},
"TrainerController.start_learning": {
"total": 7319.255898641,
"count": 1,
"self": 11.532236471017313,
"children": {
"TrainerController._reset_env": {
"total": 4.030897250999942,
"count": 1,
"self": 4.030897250999942
},
"TrainerController.advance": {
"total": 7303.0141664849825,
"count": 578571,
"self": 12.116551167609032,
"children": {
"env_step": {
"total": 5066.485913615764,
"count": 578571,
"self": 4240.9102992744565,
"children": {
"SubprocessEnvManager._take_step": {
"total": 818.0006649751837,
"count": 578571,
"self": 46.253382680857044,
"children": {
"TorchPolicy.evaluate": {
"total": 771.7472822943266,
"count": 556992,
"self": 771.7472822943266
}
}
},
"workers": {
"total": 7.574949366123747,
"count": 578571,
"self": 0.0,
"children": {
"worker_root": {
"total": 7298.032685872963,
"count": 578571,
"is_parallel": true,
"self": 3838.2276142478954,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008811339999965639,
"count": 1,
"is_parallel": true,
"self": 0.00027786099985860346,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006032730001379605,
"count": 2,
"is_parallel": true,
"self": 0.0006032730001379605
}
}
},
"UnityEnvironment.step": {
"total": 0.030352517000096668,
"count": 1,
"is_parallel": true,
"self": 0.00038562300005651196,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002136360000122295,
"count": 1,
"is_parallel": true,
"self": 0.0002136360000122295
},
"communicator.exchange": {
"total": 0.02891645099998641,
"count": 1,
"is_parallel": true,
"self": 0.02891645099998641
},
"steps_from_proto": {
"total": 0.0008368070000415173,
"count": 1,
"is_parallel": true,
"self": 0.00024648900011925434,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000590317999922263,
"count": 2,
"is_parallel": true,
"self": 0.000590317999922263
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 3459.8050716250677,
"count": 578570,
"is_parallel": true,
"self": 102.13885518608868,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 216.94312411286523,
"count": 578570,
"is_parallel": true,
"self": 216.94312411286523
},
"communicator.exchange": {
"total": 2889.218738267259,
"count": 578570,
"is_parallel": true,
"self": 2889.218738267259
},
"steps_from_proto": {
"total": 251.50435405885503,
"count": 578570,
"is_parallel": true,
"self": 95.63341125051488,
"children": {
"_process_rank_one_or_two_observation": {
"total": 155.87094280834015,
"count": 1157140,
"is_parallel": true,
"self": 155.87094280834015
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2224.411701701609,
"count": 578571,
"self": 17.74453100693745,
"children": {
"process_trajectory": {
"total": 398.4907940536683,
"count": 578571,
"self": 374.67392068866934,
"children": {
"RLTrainer._checkpoint": {
"total": 23.81687336499897,
"count": 50,
"self": 23.81687336499897
}
}
},
"_update_policy": {
"total": 1808.1763766410036,
"count": 121,
"self": 1380.2468481850028,
"children": {
"TorchPPOOptimizer.update": {
"total": 427.92952845600075,
"count": 6050,
"self": 427.92952845600075
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.6539997886866331e-06,
"count": 1,
"self": 1.6539997886866331e-06
},
"TrainerController._save_models": {
"total": 0.6785967800005892,
"count": 1,
"self": 0.024688612000318244,
"children": {
"RLTrainer._checkpoint": {
"total": 0.653908168000271,
"count": 1,
"self": 0.653908168000271
}
}
}
}
}
}
}