ppo-Huggy / run_logs /timers.json
sighmon's picture
Huggy
41501eb verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4065394401550293,
"min": 1.4065394401550293,
"max": 1.4297925233840942,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69069.5234375,
"min": 68897.0859375,
"max": 78073.75,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 88.48837209302326,
"min": 80.12175324675324,
"max": 409.9344262295082,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49465.0,
"min": 48817.0,
"max": 50125.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999954.0,
"min": 49879.0,
"max": 1999954.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999954.0,
"min": 49879.0,
"max": 1999954.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4514691829681396,
"min": -0.016536492854356766,
"max": 2.461404800415039,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1370.371337890625,
"min": -2.00091552734375,
"max": 1492.88671875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9084399421441107,
"min": 1.6052062060714753,
"max": 3.967935527338677,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2184.817927658558,
"min": 194.2299509346485,
"max": 2371.8627683520317,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9084399421441107,
"min": 1.6052062060714753,
"max": 3.967935527338677,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2184.817927658558,
"min": 194.2299509346485,
"max": 2371.8627683520317,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015073138328666068,
"min": 0.012102913763859153,
"max": 0.019688393042694464,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.045219414985998206,
"min": 0.024205827527718306,
"max": 0.05654795539157931,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05498816151585844,
"min": 0.02466989274447163,
"max": 0.058411705680191515,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1649644845475753,
"min": 0.04933978548894326,
"max": 0.17522101576129595,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5586488138166605e-06,
"min": 3.5586488138166605e-06,
"max": 0.00029533605155465,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0675946441449982e-05,
"min": 1.0675946441449982e-05,
"max": 0.0008440506186498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118618333333333,
"min": 0.10118618333333333,
"max": 0.19844535000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30355855,
"min": 0.20756065,
"max": 0.5813502,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.919054833333324e-05,
"min": 6.919054833333324e-05,
"max": 0.004922422964999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020757164499999974,
"min": 0.00020757164499999974,
"max": 0.01406937498,
"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": "1737369171",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1737371623"
},
"total": 2451.9627048830002,
"count": 1,
"self": 0.4352452349999112,
"children": {
"run_training.setup": {
"total": 0.022499479000089195,
"count": 1,
"self": 0.022499479000089195
},
"TrainerController.start_learning": {
"total": 2451.5049601690002,
"count": 1,
"self": 4.4081613679782095,
"children": {
"TrainerController._reset_env": {
"total": 3.037062457999923,
"count": 1,
"self": 3.037062457999923
},
"TrainerController.advance": {
"total": 2443.9364909930223,
"count": 231903,
"self": 4.672778009905869,
"children": {
"env_step": {
"total": 1933.9664360751394,
"count": 231903,
"self": 1521.8630690590278,
"children": {
"SubprocessEnvManager._take_step": {
"total": 409.45523329410184,
"count": 231903,
"self": 15.59936335214536,
"children": {
"TorchPolicy.evaluate": {
"total": 393.8558699419565,
"count": 222850,
"self": 393.8558699419565
}
}
},
"workers": {
"total": 2.6481337220097885,
"count": 231903,
"self": 0.0,
"children": {
"worker_root": {
"total": 2444.0033453740257,
"count": 231903,
"is_parallel": true,
"self": 1203.0101338919562,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009681569999884232,
"count": 1,
"is_parallel": true,
"self": 0.0002588819999118641,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007092750000765591,
"count": 2,
"is_parallel": true,
"self": 0.0007092750000765591
}
}
},
"UnityEnvironment.step": {
"total": 0.053989377999982935,
"count": 1,
"is_parallel": true,
"self": 0.00030817800006843754,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021112899992203893,
"count": 1,
"is_parallel": true,
"self": 0.00021112899992203893
},
"communicator.exchange": {
"total": 0.052671337999981915,
"count": 1,
"is_parallel": true,
"self": 0.052671337999981915
},
"steps_from_proto": {
"total": 0.000798733000010543,
"count": 1,
"is_parallel": true,
"self": 0.00017789200001061545,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006208409999999276,
"count": 2,
"is_parallel": true,
"self": 0.0006208409999999276
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1240.9932114820695,
"count": 231902,
"is_parallel": true,
"self": 37.49240616917041,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.2966437018697,
"count": 231902,
"is_parallel": true,
"self": 80.2966437018697
},
"communicator.exchange": {
"total": 1034.8075574710194,
"count": 231902,
"is_parallel": true,
"self": 1034.8075574710194
},
"steps_from_proto": {
"total": 88.39660414000991,
"count": 231902,
"is_parallel": true,
"self": 32.507755624041124,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.88884851596879,
"count": 463804,
"is_parallel": true,
"self": 55.88884851596879
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 505.2972769079771,
"count": 231903,
"self": 6.784299282016491,
"children": {
"process_trajectory": {
"total": 160.27065088096276,
"count": 231903,
"self": 158.95218250596258,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3184683750001795,
"count": 10,
"self": 1.3184683750001795
}
}
},
"_update_policy": {
"total": 338.24232674499785,
"count": 97,
"self": 269.51183790000937,
"children": {
"TorchPPOOptimizer.update": {
"total": 68.73048884498849,
"count": 2910,
"self": 68.73048884498849
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.699998943484388e-07,
"count": 1,
"self": 8.699998943484388e-07
},
"TrainerController._save_models": {
"total": 0.12324447999981203,
"count": 1,
"self": 0.0018360250001023815,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12140845499970965,
"count": 1,
"self": 0.12140845499970965
}
}
}
}
}
}
}