ppo-Huggy / run_logs /timers.json
Casio991ms's picture
Huggy
cd9fa80 verified
raw
history blame
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4106589555740356,
"min": 1.4106589555740356,
"max": 1.4289169311523438,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71265.078125,
"min": 68223.3046875,
"max": 78053.0234375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 86.7,
"min": 80.29159802306425,
"max": 393.00787401574803,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49419.0,
"min": 48737.0,
"max": 50170.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999962.0,
"min": 49945.0,
"max": 1999962.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999962.0,
"min": 49945.0,
"max": 1999962.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.395406484603882,
"min": 0.04861318692564964,
"max": 2.487588882446289,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1365.3817138671875,
"min": 6.1252617835998535,
"max": 1470.97802734375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7154561508120154,
"min": 1.8343144137234915,
"max": 4.00881972743126,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2117.8100059628487,
"min": 231.12361612915993,
"max": 2377.2300983667374,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7154561508120154,
"min": 1.8343144137234915,
"max": 4.00881972743126,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2117.8100059628487,
"min": 231.12361612915993,
"max": 2377.2300983667374,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0170457308465201,
"min": 0.013452435206757703,
"max": 0.021517593774478882,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0511371925395603,
"min": 0.026904870413515407,
"max": 0.0583582578226924,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06238491117126412,
"min": 0.023553997837007047,
"max": 0.06238491117126412,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18715473351379236,
"min": 0.047107995674014094,
"max": 0.18715473351379236,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.423048859016668e-06,
"min": 3.423048859016668e-06,
"max": 0.00029534025155324997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0269146577050003e-05,
"min": 1.0269146577050003e-05,
"max": 0.0008442378185874001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114098333333336,
"min": 0.10114098333333336,
"max": 0.19844674999999992,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034229500000001,
"min": 0.20741955,
"max": 0.5814126,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.693506833333339e-05,
"min": 6.693506833333339e-05,
"max": 0.004922492824999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020080520500000016,
"min": 0.00020080520500000016,
"max": 0.014072488740000002,
"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": "1708952002",
"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": "1708954452"
},
"total": 2450.2574816409997,
"count": 1,
"self": 0.4341068709995852,
"children": {
"run_training.setup": {
"total": 0.0524969590001092,
"count": 1,
"self": 0.0524969590001092
},
"TrainerController.start_learning": {
"total": 2449.770877811,
"count": 1,
"self": 4.641668361024131,
"children": {
"TrainerController._reset_env": {
"total": 3.1066309210000327,
"count": 1,
"self": 3.1066309210000327
},
"TrainerController.advance": {
"total": 2441.905296024976,
"count": 232067,
"self": 4.898988734966679,
"children": {
"env_step": {
"total": 1972.1734007249959,
"count": 232067,
"self": 1633.1797311669422,
"children": {
"SubprocessEnvManager._take_step": {
"total": 335.9766610149113,
"count": 232067,
"self": 17.856420459898573,
"children": {
"TorchPolicy.evaluate": {
"total": 318.12024055501274,
"count": 223021,
"self": 318.12024055501274
}
}
},
"workers": {
"total": 3.0170085431423104,
"count": 232067,
"self": 0.0,
"children": {
"worker_root": {
"total": 2442.2514573740405,
"count": 232067,
"is_parallel": true,
"self": 1113.7653951351263,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010092089999034215,
"count": 1,
"is_parallel": true,
"self": 0.00028189999989081116,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007273090000126103,
"count": 2,
"is_parallel": true,
"self": 0.0007273090000126103
}
}
},
"UnityEnvironment.step": {
"total": 0.03143294000005881,
"count": 1,
"is_parallel": true,
"self": 0.00037621699993906077,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002124929999354208,
"count": 1,
"is_parallel": true,
"self": 0.0002124929999354208
},
"communicator.exchange": {
"total": 0.030033546000140632,
"count": 1,
"is_parallel": true,
"self": 0.030033546000140632
},
"steps_from_proto": {
"total": 0.0008106840000436932,
"count": 1,
"is_parallel": true,
"self": 0.00022091400001045258,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005897700000332406,
"count": 2,
"is_parallel": true,
"self": 0.0005897700000332406
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1328.4860622389142,
"count": 232066,
"is_parallel": true,
"self": 42.092947421897634,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.55585102513578,
"count": 232066,
"is_parallel": true,
"self": 87.55585102513578
},
"communicator.exchange": {
"total": 1103.1081234769135,
"count": 232066,
"is_parallel": true,
"self": 1103.1081234769135
},
"steps_from_proto": {
"total": 95.72914031496725,
"count": 232066,
"is_parallel": true,
"self": 35.798924799936685,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.93021551503057,
"count": 464132,
"is_parallel": true,
"self": 59.93021551503057
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 464.8329065650132,
"count": 232067,
"self": 7.055918739180697,
"children": {
"process_trajectory": {
"total": 156.97184093983196,
"count": 232067,
"self": 155.65805566483186,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3137852750001002,
"count": 10,
"self": 1.3137852750001002
}
}
},
"_update_policy": {
"total": 300.80514688600056,
"count": 97,
"self": 239.02248981899766,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.7826570670029,
"count": 2910,
"self": 61.7826570670029
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.379997780139092e-07,
"count": 1,
"self": 8.379997780139092e-07
},
"TrainerController._save_models": {
"total": 0.11728166600005352,
"count": 1,
"self": 0.0019360430001142959,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11534562299993922,
"count": 1,
"self": 0.11534562299993922
}
}
}
}
}
}
}