ppo-Huggy / run_logs /timers.json
FlippyCode's picture
Huggy
f722f79 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4060722589492798,
"min": 1.4060722589492798,
"max": 1.4307180643081665,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71466.4375,
"min": 67546.9375,
"max": 76281.4375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 110.59555555555555,
"min": 101.72633744855968,
"max": 417.801652892562,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49768.0,
"min": 48816.0,
"max": 50554.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999476.0,
"min": 49925.0,
"max": 1999476.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999476.0,
"min": 49925.0,
"max": 1999476.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.353079080581665,
"min": -0.00396215682849288,
"max": 2.353079080581665,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1058.8856201171875,
"min": -0.4754588305950165,
"max": 1130.20458984375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.74578541331821,
"min": 1.8029420644044876,
"max": 3.757125649157734,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1685.6034359931946,
"min": 216.3530477285385,
"max": 1764.6669425964355,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.74578541331821,
"min": 1.8029420644044876,
"max": 3.757125649157734,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1685.6034359931946,
"min": 216.3530477285385,
"max": 1764.6669425964355,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019065482618558845,
"min": 0.014239453130721813,
"max": 0.01945890453320721,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03813096523711769,
"min": 0.028478906261443625,
"max": 0.058376713599621634,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04717858557899793,
"min": 0.021924107739080986,
"max": 0.0603360446376933,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09435717115799586,
"min": 0.04384821547816197,
"max": 0.1810081339130799,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.616198461299994e-06,
"min": 4.616198461299994e-06,
"max": 0.00029523892658702496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.232396922599988e-06,
"min": 9.232396922599988e-06,
"max": 0.0008438064187311998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10153869999999998,
"min": 0.10153869999999998,
"max": 0.19841297500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20307739999999996,
"min": 0.20307739999999996,
"max": 0.5812688,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.678112999999994e-05,
"min": 8.678112999999994e-05,
"max": 0.004920807452499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017356225999999987,
"min": 0.00017356225999999987,
"max": 0.01406531312,
"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": "1709002228",
"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": "1709004564"
},
"total": 2335.7514733249996,
"count": 1,
"self": 0.43807109599993055,
"children": {
"run_training.setup": {
"total": 0.048820912999872235,
"count": 1,
"self": 0.048820912999872235
},
"TrainerController.start_learning": {
"total": 2335.2645813159997,
"count": 1,
"self": 4.353737861050831,
"children": {
"TrainerController._reset_env": {
"total": 3.431015541999841,
"count": 1,
"self": 3.431015541999841
},
"TrainerController.advance": {
"total": 2327.360599776948,
"count": 230862,
"self": 4.598550212003374,
"children": {
"env_step": {
"total": 1857.8306476690127,
"count": 230862,
"self": 1538.3422521021425,
"children": {
"SubprocessEnvManager._take_step": {
"total": 316.83726944683076,
"count": 230862,
"self": 16.918816561924814,
"children": {
"TorchPolicy.evaluate": {
"total": 299.91845288490595,
"count": 223027,
"self": 299.91845288490595
}
}
},
"workers": {
"total": 2.6511261200394074,
"count": 230862,
"self": 0.0,
"children": {
"worker_root": {
"total": 2328.2463976352137,
"count": 230862,
"is_parallel": true,
"self": 1073.9480569830826,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008647939998809306,
"count": 1,
"is_parallel": true,
"self": 0.00025334100018881145,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006114529996921192,
"count": 2,
"is_parallel": true,
"self": 0.0006114529996921192
}
}
},
"UnityEnvironment.step": {
"total": 0.03009991099997933,
"count": 1,
"is_parallel": true,
"self": 0.00039253400018424145,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021457699995153234,
"count": 1,
"is_parallel": true,
"self": 0.00021457699995153234
},
"communicator.exchange": {
"total": 0.028726929999720596,
"count": 1,
"is_parallel": true,
"self": 0.028726929999720596
},
"steps_from_proto": {
"total": 0.000765870000122959,
"count": 1,
"is_parallel": true,
"self": 0.00021952100041744416,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005463489997055149,
"count": 2,
"is_parallel": true,
"self": 0.0005463489997055149
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1254.2983406521312,
"count": 230861,
"is_parallel": true,
"self": 40.737119322092894,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.7918490060315,
"count": 230861,
"is_parallel": true,
"self": 80.7918490060315
},
"communicator.exchange": {
"total": 1043.4743993850707,
"count": 230861,
"is_parallel": true,
"self": 1043.4743993850707
},
"steps_from_proto": {
"total": 89.2949729389361,
"count": 230861,
"is_parallel": true,
"self": 31.281513786756022,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.013459152180076,
"count": 461722,
"is_parallel": true,
"self": 58.013459152180076
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 464.93140189593214,
"count": 230862,
"self": 6.485582468151279,
"children": {
"process_trajectory": {
"total": 139.17824835677902,
"count": 230862,
"self": 137.94930189578008,
"children": {
"RLTrainer._checkpoint": {
"total": 1.228946460998941,
"count": 10,
"self": 1.228946460998941
}
}
},
"_update_policy": {
"total": 319.26757107100184,
"count": 96,
"self": 256.0793484260312,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.188222644970665,
"count": 2880,
"self": 63.188222644970665
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.640008672955446e-07,
"count": 1,
"self": 8.640008672955446e-07
},
"TrainerController._save_models": {
"total": 0.11922727199998917,
"count": 1,
"self": 0.0019581910000852076,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11726908099990396,
"count": 1,
"self": 0.11726908099990396
}
}
}
}
}
}
}