ppo-Huggy / run_logs /timers.json
alidenewade's picture
Huggy
8fc9879 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.403813362121582,
"min": 1.403813362121582,
"max": 1.4246387481689453,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69960.4453125,
"min": 68718.625,
"max": 76639.4609375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 88.37388193202146,
"min": 77.56985871271586,
"max": 400.6666666666667,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49401.0,
"min": 48756.0,
"max": 50484.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999992.0,
"min": 49860.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999992.0,
"min": 49860.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4995453357696533,
"min": 0.009167427197098732,
"max": 2.541478157043457,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1397.245849609375,
"min": 1.1459283828735352,
"max": 1546.1263427734375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9398524166219775,
"min": 1.6980383145809173,
"max": 4.0320881698872935,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2202.3775008916855,
"min": 212.25478932261467,
"max": 2422.3329184651375,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9398524166219775,
"min": 1.6980383145809173,
"max": 4.0320881698872935,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2202.3775008916855,
"min": 212.25478932261467,
"max": 2422.3329184651375,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016934100554660998,
"min": 0.013780243565815909,
"max": 0.01902742478317426,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.050802301663982995,
"min": 0.027560487131631818,
"max": 0.056290721274369085,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05635601352486345,
"min": 0.0233655107828478,
"max": 0.06429927311837673,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16906804057459035,
"min": 0.0467310215656956,
"max": 0.19083093442022803,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4498488500833298e-06,
"min": 3.4498488500833298e-06,
"max": 0.00029529232656922495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.034954655024999e-05,
"min": 1.034954655024999e-05,
"max": 0.0008438611687129501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114991666666666,
"min": 0.10114991666666666,
"max": 0.19843077500000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30344974999999996,
"min": 0.20746694999999998,
"max": 0.5812870499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.73808416666666e-05,
"min": 6.73808416666666e-05,
"max": 0.0049216956725,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020214252499999982,
"min": 0.00020214252499999982,
"max": 0.014066223794999999,
"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": "1719639423",
"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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1719641774"
},
"total": 2351.0056464550003,
"count": 1,
"self": 0.44220266000002084,
"children": {
"run_training.setup": {
"total": 0.057888992000016515,
"count": 1,
"self": 0.057888992000016515
},
"TrainerController.start_learning": {
"total": 2350.505554803,
"count": 1,
"self": 4.150314643983165,
"children": {
"TrainerController._reset_env": {
"total": 3.682983854999975,
"count": 1,
"self": 3.682983854999975
},
"TrainerController.advance": {
"total": 2342.5645088180167,
"count": 232569,
"self": 4.863548664018708,
"children": {
"env_step": {
"total": 1857.5066567879385,
"count": 232569,
"self": 1534.549516640875,
"children": {
"SubprocessEnvManager._take_step": {
"total": 320.2094437780348,
"count": 232569,
"self": 16.954917969067537,
"children": {
"TorchPolicy.evaluate": {
"total": 303.2545258089673,
"count": 222937,
"self": 303.2545258089673
}
}
},
"workers": {
"total": 2.7476963690285174,
"count": 232569,
"self": 0.0,
"children": {
"worker_root": {
"total": 2343.7099048979976,
"count": 232569,
"is_parallel": true,
"self": 1110.243698175926,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009881539999696543,
"count": 1,
"is_parallel": true,
"self": 0.00027120400000058,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007169499999690743,
"count": 2,
"is_parallel": true,
"self": 0.0007169499999690743
}
}
},
"UnityEnvironment.step": {
"total": 0.0294300220000423,
"count": 1,
"is_parallel": true,
"self": 0.00039531800007353013,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020779299995865586,
"count": 1,
"is_parallel": true,
"self": 0.00020779299995865586
},
"communicator.exchange": {
"total": 0.028072018999978354,
"count": 1,
"is_parallel": true,
"self": 0.028072018999978354
},
"steps_from_proto": {
"total": 0.0007548920000317594,
"count": 1,
"is_parallel": true,
"self": 0.00019895400009772857,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005559379999340308,
"count": 2,
"is_parallel": true,
"self": 0.0005559379999340308
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1233.4662067220715,
"count": 232568,
"is_parallel": true,
"self": 38.092593809074515,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.7135469710687,
"count": 232568,
"is_parallel": true,
"self": 79.7135469710687
},
"communicator.exchange": {
"total": 1028.0758639459245,
"count": 232568,
"is_parallel": true,
"self": 1028.0758639459245
},
"steps_from_proto": {
"total": 87.5842019960038,
"count": 232568,
"is_parallel": true,
"self": 30.89787681996563,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.68632517603817,
"count": 465136,
"is_parallel": true,
"self": 56.68632517603817
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 480.19430336605944,
"count": 232569,
"self": 6.254876910020357,
"children": {
"process_trajectory": {
"total": 151.0760546390395,
"count": 232569,
"self": 149.67615876303933,
"children": {
"RLTrainer._checkpoint": {
"total": 1.399895876000187,
"count": 10,
"self": 1.399895876000187
}
}
},
"_update_policy": {
"total": 322.8633718169996,
"count": 97,
"self": 260.11467682700743,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.748694989992146,
"count": 2910,
"self": 62.748694989992146
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.090003914025147e-07,
"count": 1,
"self": 9.090003914025147e-07
},
"TrainerController._save_models": {
"total": 0.1077465769999435,
"count": 1,
"self": 0.0022257109999372915,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10552086600000621,
"count": 1,
"self": 0.10552086600000621
}
}
}
}
}
}
}