ppo-Huggy / run_logs /timers.json
FarStryke21's picture
Huggy
006cff1 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.408075213432312,
"min": 1.408075213432312,
"max": 1.4284833669662476,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70527.671875,
"min": 68683.375,
"max": 76238.7265625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 100.07474747474747,
"min": 91.52310536044362,
"max": 430.71794871794873,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49537.0,
"min": 48825.0,
"max": 50394.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999959.0,
"min": 49762.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999959.0,
"min": 49762.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3156514167785645,
"min": 0.09704208374023438,
"max": 2.3897414207458496,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1146.2474365234375,
"min": 11.256881713867188,
"max": 1256.21923828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.575830101485204,
"min": 1.9829967204352905,
"max": 3.913063565971925,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1770.035900235176,
"min": 230.0276195704937,
"max": 1998.3836035728455,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.575830101485204,
"min": 1.9829967204352905,
"max": 3.913063565971925,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1770.035900235176,
"min": 230.0276195704937,
"max": 1998.3836035728455,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0147725615951155,
"min": 0.014601106392850246,
"max": 0.019871201515585805,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.029545123190231,
"min": 0.029202212785700492,
"max": 0.057846626194077544,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05367206539958715,
"min": 0.023413620702922345,
"max": 0.06343252006918192,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1073441307991743,
"min": 0.04682724140584469,
"max": 0.16671611902614433,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.310873563074999e-06,
"min": 4.310873563074999e-06,
"max": 0.000295326526557825,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.621747126149999e-06,
"min": 8.621747126149999e-06,
"max": 0.0008437293187569001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10143692500000001,
"min": 0.10143692500000001,
"max": 0.19844217500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20287385000000002,
"min": 0.20287385000000002,
"max": 0.5812431,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.170255749999999e-05,
"min": 8.170255749999999e-05,
"max": 0.0049222645325,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016340511499999999,
"min": 0.00016340511499999999,
"max": 0.014064030690000003,
"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": "1731686872",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1731689514"
},
"total": 2642.033482847,
"count": 1,
"self": 0.4369270309998683,
"children": {
"run_training.setup": {
"total": 0.08326888499993856,
"count": 1,
"self": 0.08326888499993856
},
"TrainerController.start_learning": {
"total": 2641.513286931,
"count": 1,
"self": 5.2432015610738745,
"children": {
"TrainerController._reset_env": {
"total": 5.524798238000017,
"count": 1,
"self": 5.524798238000017
},
"TrainerController.advance": {
"total": 2630.632586457926,
"count": 231204,
"self": 5.33431713004984,
"children": {
"env_step": {
"total": 2115.7651677200083,
"count": 231204,
"self": 1664.1733065829753,
"children": {
"SubprocessEnvManager._take_step": {
"total": 448.21367652192987,
"count": 231204,
"self": 18.305102307939137,
"children": {
"TorchPolicy.evaluate": {
"total": 429.90857421399073,
"count": 222956,
"self": 429.90857421399073
}
}
},
"workers": {
"total": 3.378184615103123,
"count": 231204,
"self": 0.0,
"children": {
"worker_root": {
"total": 2633.3924390531442,
"count": 231204,
"is_parallel": true,
"self": 1291.7871028091763,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010634939999363269,
"count": 1,
"is_parallel": true,
"self": 0.00032374099987464433,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007397530000616825,
"count": 2,
"is_parallel": true,
"self": 0.0007397530000616825
}
}
},
"UnityEnvironment.step": {
"total": 0.030259728000032737,
"count": 1,
"is_parallel": true,
"self": 0.0003831340001170247,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021172399999613845,
"count": 1,
"is_parallel": true,
"self": 0.00021172399999613845
},
"communicator.exchange": {
"total": 0.02888119299996106,
"count": 1,
"is_parallel": true,
"self": 0.02888119299996106
},
"steps_from_proto": {
"total": 0.0007836769999585158,
"count": 1,
"is_parallel": true,
"self": 0.00021025399996688066,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005734229999916352,
"count": 2,
"is_parallel": true,
"self": 0.0005734229999916352
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1341.605336243968,
"count": 231203,
"is_parallel": true,
"self": 41.84521514282983,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.74051561607632,
"count": 231203,
"is_parallel": true,
"self": 84.74051561607632
},
"communicator.exchange": {
"total": 1115.8386330119881,
"count": 231203,
"is_parallel": true,
"self": 1115.8386330119881
},
"steps_from_proto": {
"total": 99.18097247307355,
"count": 231203,
"is_parallel": true,
"self": 36.21097263806462,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.969999835008934,
"count": 462406,
"is_parallel": true,
"self": 62.969999835008934
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 509.53310160786793,
"count": 231204,
"self": 8.164432765850279,
"children": {
"process_trajectory": {
"total": 170.93411244601816,
"count": 231204,
"self": 169.5980253200181,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3360871260000522,
"count": 10,
"self": 1.3360871260000522
}
}
},
"_update_policy": {
"total": 330.4345563959995,
"count": 96,
"self": 264.81957434800586,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.61498204799364,
"count": 2880,
"self": 65.61498204799364
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.119999049289618e-07,
"count": 1,
"self": 9.119999049289618e-07
},
"TrainerController._save_models": {
"total": 0.11269976199992016,
"count": 1,
"self": 0.002326673999959894,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11037308799996026,
"count": 1,
"self": 0.11037308799996026
}
}
}
}
}
}
}