ppo-Huggy / run_logs /timers.json
Suprim003's picture
Huggy
5aecd2b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4037353992462158,
"min": 1.4037353992462158,
"max": 1.429650068283081,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70790.375,
"min": 68558.9609375,
"max": 76186.9140625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 93.13780260707635,
"min": 86.66373239436619,
"max": 390.4453125,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50015.0,
"min": 49071.0,
"max": 50251.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999827.0,
"min": 49558.0,
"max": 1999827.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999827.0,
"min": 49558.0,
"max": 1999827.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4375035762786865,
"min": 0.14973518252372742,
"max": 2.476517915725708,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1308.939453125,
"min": 19.016368865966797,
"max": 1353.12109375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6567293130263714,
"min": 1.9357144874850596,
"max": 3.8651616814726832,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1963.6636410951614,
"min": 245.83573991060257,
"max": 2065.6398829221725,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6567293130263714,
"min": 1.9357144874850596,
"max": 3.8651616814726832,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1963.6636410951614,
"min": 245.83573991060257,
"max": 2065.6398829221725,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01740522362330618,
"min": 0.014051497240628427,
"max": 0.020020614735858547,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05221567086991853,
"min": 0.028102994481256853,
"max": 0.05344161630734258,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05423576757311821,
"min": 0.022851413767784833,
"max": 0.07200076604882877,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16270730271935463,
"min": 0.045702827535569666,
"max": 0.19620025008916853,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2394489202166624e-06,
"min": 3.2394489202166624e-06,
"max": 0.00029534850155049994,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.718346760649987e-06,
"min": 9.718346760649987e-06,
"max": 0.0008437411687529498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10107978333333338,
"min": 0.10107978333333338,
"max": 0.19844949999999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30323935000000013,
"min": 0.2073063,
"max": 0.58124705,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.38811883333333e-05,
"min": 6.38811883333333e-05,
"max": 0.004922630050000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019164356499999988,
"min": 0.00019164356499999988,
"max": 0.014064227795000002,
"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": "1752562317",
"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 --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1752565532"
},
"total": 3214.417379798,
"count": 1,
"self": 0.5837639920000584,
"children": {
"run_training.setup": {
"total": 0.03330561799998577,
"count": 1,
"self": 0.03330561799998577
},
"TrainerController.start_learning": {
"total": 3213.800310188,
"count": 1,
"self": 6.146522666160308,
"children": {
"TrainerController._reset_env": {
"total": 3.5896940590000668,
"count": 1,
"self": 3.5896940590000668
},
"TrainerController.advance": {
"total": 3203.90202315084,
"count": 231428,
"self": 6.2381835148821665,
"children": {
"env_step": {
"total": 2377.42887190693,
"count": 231428,
"self": 1800.5752436830023,
"children": {
"SubprocessEnvManager._take_step": {
"total": 572.9161630750432,
"count": 231428,
"self": 22.083385870080065,
"children": {
"TorchPolicy.evaluate": {
"total": 550.8327772049631,
"count": 222988,
"self": 550.8327772049631
}
}
},
"workers": {
"total": 3.9374651488844847,
"count": 231428,
"self": 0.0,
"children": {
"worker_root": {
"total": 3205.858654201903,
"count": 231428,
"is_parallel": true,
"self": 1820.6966168359763,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009514319999652798,
"count": 1,
"is_parallel": true,
"self": 0.00030313599995679397,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006482960000084859,
"count": 2,
"is_parallel": true,
"self": 0.0006482960000084859
}
}
},
"UnityEnvironment.step": {
"total": 0.04870771300011256,
"count": 1,
"is_parallel": true,
"self": 0.00034512399997765897,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001821270000164077,
"count": 1,
"is_parallel": true,
"self": 0.0001821270000164077
},
"communicator.exchange": {
"total": 0.04753570499997295,
"count": 1,
"is_parallel": true,
"self": 0.04753570499997295
},
"steps_from_proto": {
"total": 0.000644757000145546,
"count": 1,
"is_parallel": true,
"self": 0.00016134000043166452,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004834169997138815,
"count": 2,
"is_parallel": true,
"self": 0.0004834169997138815
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1385.1620373659266,
"count": 231427,
"is_parallel": true,
"self": 37.11883466088125,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.2952295499706,
"count": 231427,
"is_parallel": true,
"self": 85.2952295499706
},
"communicator.exchange": {
"total": 1174.6994501211184,
"count": 231427,
"is_parallel": true,
"self": 1174.6994501211184
},
"steps_from_proto": {
"total": 88.04852303395637,
"count": 231427,
"is_parallel": true,
"self": 31.142316242670404,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.90620679128597,
"count": 462854,
"is_parallel": true,
"self": 56.90620679128597
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 820.2349677290276,
"count": 231428,
"self": 9.448889439986488,
"children": {
"process_trajectory": {
"total": 246.58391101404277,
"count": 231428,
"self": 244.83019255604313,
"children": {
"RLTrainer._checkpoint": {
"total": 1.7537184579996392,
"count": 10,
"self": 1.7537184579996392
}
}
},
"_update_policy": {
"total": 564.2021672749984,
"count": 97,
"self": 473.56166073399095,
"children": {
"TorchPPOOptimizer.update": {
"total": 90.64050654100743,
"count": 2910,
"self": 90.64050654100743
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2239997886354104e-06,
"count": 1,
"self": 1.2239997886354104e-06
},
"TrainerController._save_models": {
"total": 0.1620690879999529,
"count": 1,
"self": 0.002259993999359722,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15980909400059318,
"count": 1,
"self": 0.15980909400059318
}
}
}
}
}
}
}