ppo-Huggy / run_logs /timers.json
stuvx's picture
Huggy
349b43a verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4022129774093628,
"min": 1.4022129774093628,
"max": 1.4287285804748535,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70103.640625,
"min": 69458.734375,
"max": 76981.8828125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 82.35973597359735,
"min": 75.66203703703704,
"max": 389.1162790697674,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49910.0,
"min": 48811.0,
"max": 50196.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999807.0,
"min": 49575.0,
"max": 1999807.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999807.0,
"min": 49575.0,
"max": 1999807.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4946823120117188,
"min": 0.1712605059146881,
"max": 2.4996542930603027,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1511.7774658203125,
"min": 21.921344757080078,
"max": 1585.625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8394805895219934,
"min": 1.7548565117176622,
"max": 3.9625047038577192,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2326.725237250328,
"min": 224.62163349986076,
"max": 2443.1875874996185,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8394805895219934,
"min": 1.7548565117176622,
"max": 3.9625047038577192,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2326.725237250328,
"min": 224.62163349986076,
"max": 2443.1875874996185,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01708395506462289,
"min": 0.013823339433292859,
"max": 0.021166646773821813,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05125186519386868,
"min": 0.027646678866585717,
"max": 0.06349994032146544,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.059968708538346814,
"min": 0.021547913334021965,
"max": 0.06225954517722129,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17990612561504044,
"min": 0.04309582666804393,
"max": 0.17990612561504044,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.573848808749998e-06,
"min": 3.573848808749998e-06,
"max": 0.000295371076542975,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0721546426249994e-05,
"min": 1.0721546426249994e-05,
"max": 0.0008441184186272,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10119124999999997,
"min": 0.10119124999999997,
"max": 0.198457025,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035737499999999,
"min": 0.20752765000000006,
"max": 0.5813728,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.944337499999996e-05,
"min": 6.944337499999996e-05,
"max": 0.0049230055475,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020833012499999989,
"min": 0.00020833012499999989,
"max": 0.014070502720000003,
"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": "1713646260",
"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": "1713648583"
},
"total": 2323.466617735,
"count": 1,
"self": 0.3894868709999173,
"children": {
"run_training.setup": {
"total": 0.054365097000015794,
"count": 1,
"self": 0.054365097000015794
},
"TrainerController.start_learning": {
"total": 2323.0227657670002,
"count": 1,
"self": 4.113530108838859,
"children": {
"TrainerController._reset_env": {
"total": 3.2947451079999723,
"count": 1,
"self": 3.2947451079999723
},
"TrainerController.advance": {
"total": 2315.493219836161,
"count": 232437,
"self": 4.491744760279744,
"children": {
"env_step": {
"total": 1838.532181703942,
"count": 232437,
"self": 1527.237910999891,
"children": {
"SubprocessEnvManager._take_step": {
"total": 308.6032669849901,
"count": 232437,
"self": 16.15559967212289,
"children": {
"TorchPolicy.evaluate": {
"total": 292.4476673128672,
"count": 222908,
"self": 292.4476673128672
}
}
},
"workers": {
"total": 2.6910037190607454,
"count": 232437,
"self": 0.0,
"children": {
"worker_root": {
"total": 2316.1179955849216,
"count": 232437,
"is_parallel": true,
"self": 1082.963672669895,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000998616000003949,
"count": 1,
"is_parallel": true,
"self": 0.00024773600000571605,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000750879999998233,
"count": 2,
"is_parallel": true,
"self": 0.000750879999998233
}
}
},
"UnityEnvironment.step": {
"total": 0.028612328000008347,
"count": 1,
"is_parallel": true,
"self": 0.00041520199999922625,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001986949999945864,
"count": 1,
"is_parallel": true,
"self": 0.0001986949999945864
},
"communicator.exchange": {
"total": 0.027254867999999988,
"count": 1,
"is_parallel": true,
"self": 0.027254867999999988
},
"steps_from_proto": {
"total": 0.0007435630000145466,
"count": 1,
"is_parallel": true,
"self": 0.000202642999965974,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005409200000485725,
"count": 2,
"is_parallel": true,
"self": 0.0005409200000485725
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1233.1543229150266,
"count": 232436,
"is_parallel": true,
"self": 38.871318029038775,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.75033175800695,
"count": 232436,
"is_parallel": true,
"self": 81.75033175800695
},
"communicator.exchange": {
"total": 1023.8259812409522,
"count": 232436,
"is_parallel": true,
"self": 1023.8259812409522
},
"steps_from_proto": {
"total": 88.70669188702868,
"count": 232436,
"is_parallel": true,
"self": 32.02459495105825,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.682096935970435,
"count": 464872,
"is_parallel": true,
"self": 56.682096935970435
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 472.46929337193967,
"count": 232437,
"self": 6.162092711983007,
"children": {
"process_trajectory": {
"total": 145.40460317095864,
"count": 232437,
"self": 144.19873429195928,
"children": {
"RLTrainer._checkpoint": {
"total": 1.205868878999354,
"count": 10,
"self": 1.205868878999354
}
}
},
"_update_policy": {
"total": 320.902597488998,
"count": 97,
"self": 258.6716434569985,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.230954031999545,
"count": 2910,
"self": 62.230954031999545
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.350001164420974e-07,
"count": 1,
"self": 9.350001164420974e-07
},
"TrainerController._save_models": {
"total": 0.12126977900015845,
"count": 1,
"self": 0.0019694710003932414,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11930030799976521,
"count": 1,
"self": 0.11930030799976521
}
}
}
}
}
}
}