ppo-Huggy / run_logs /timers.json
madmage's picture
Huggy
a265294 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4017524719238281,
"min": 1.4017524719238281,
"max": 1.4268343448638916,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70885.21875,
"min": 68965.3828125,
"max": 74741.7890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.10443037974683,
"min": 74.74242424242425,
"max": 416.05833333333334,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49994.0,
"min": 48876.0,
"max": 50122.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999911.0,
"min": 49974.0,
"max": 1999911.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999911.0,
"min": 49974.0,
"max": 1999911.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.51019549369812,
"min": 0.05099547654390335,
"max": 2.51019549369812,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1586.443603515625,
"min": 6.068461894989014,
"max": 1635.47509765625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9751369891853274,
"min": 1.720363842339075,
"max": 4.0016307412513665,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2512.286577165127,
"min": 204.72329723834991,
"max": 2560.043298482895,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9751369891853274,
"min": 1.720363842339075,
"max": 4.0016307412513665,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2512.286577165127,
"min": 204.72329723834991,
"max": 2560.043298482895,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015474034362705426,
"min": 0.013884329944145672,
"max": 0.020638690297103798,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04642210308811628,
"min": 0.02875239338670023,
"max": 0.055536858443520035,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05998673455582724,
"min": 0.022856231747816008,
"max": 0.06490741167217493,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17996020366748172,
"min": 0.045712463495632016,
"max": 0.19339904102186362,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.685448771550008e-06,
"min": 3.685448771550008e-06,
"max": 0.00029528602657132497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1056346314650025e-05,
"min": 1.1056346314650025e-05,
"max": 0.0008440654686448499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10122845000000003,
"min": 0.10122845000000003,
"max": 0.19842867500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3036853500000001,
"min": 0.2076015000000001,
"max": 0.58135515,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.129965500000017e-05,
"min": 7.129965500000017e-05,
"max": 0.004921590882499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002138989650000005,
"min": 0.0002138989650000005,
"max": 0.014069621985,
"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": "1742575623",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1742578245"
},
"total": 2622.560429712,
"count": 1,
"self": 0.49241249600027004,
"children": {
"run_training.setup": {
"total": 0.02512798999998722,
"count": 1,
"self": 0.02512798999998722
},
"TrainerController.start_learning": {
"total": 2622.0428892259997,
"count": 1,
"self": 4.875841179870804,
"children": {
"TrainerController._reset_env": {
"total": 3.0031539299999395,
"count": 1,
"self": 3.0031539299999395
},
"TrainerController.advance": {
"total": 2614.0274228561293,
"count": 233067,
"self": 5.058328783022716,
"children": {
"env_step": {
"total": 2094.647081016178,
"count": 233067,
"self": 1636.8009478612078,
"children": {
"SubprocessEnvManager._take_step": {
"total": 454.7861828490427,
"count": 233067,
"self": 16.765408479076882,
"children": {
"TorchPolicy.evaluate": {
"total": 438.0207743699658,
"count": 222944,
"self": 438.0207743699658
}
}
},
"workers": {
"total": 3.059950305927714,
"count": 233067,
"self": 0.0,
"children": {
"worker_root": {
"total": 2613.957276692041,
"count": 233067,
"is_parallel": true,
"self": 1281.767722419108,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010628310000129204,
"count": 1,
"is_parallel": true,
"self": 0.0003966929999705826,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006661380000423378,
"count": 2,
"is_parallel": true,
"self": 0.0006661380000423378
}
}
},
"UnityEnvironment.step": {
"total": 0.03156809600000088,
"count": 1,
"is_parallel": true,
"self": 0.0003416050001305848,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019005399997240602,
"count": 1,
"is_parallel": true,
"self": 0.00019005399997240602
},
"communicator.exchange": {
"total": 0.030280708999953276,
"count": 1,
"is_parallel": true,
"self": 0.030280708999953276
},
"steps_from_proto": {
"total": 0.0007557279999446109,
"count": 1,
"is_parallel": true,
"self": 0.00021939399994153064,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005363340000030803,
"count": 2,
"is_parallel": true,
"self": 0.0005363340000030803
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1332.189554272933,
"count": 233066,
"is_parallel": true,
"self": 38.78900492977186,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.69253710497514,
"count": 233066,
"is_parallel": true,
"self": 86.69253710497514
},
"communicator.exchange": {
"total": 1114.0019498570973,
"count": 233066,
"is_parallel": true,
"self": 1114.0019498570973
},
"steps_from_proto": {
"total": 92.70606238108871,
"count": 233066,
"is_parallel": true,
"self": 34.43648319106478,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.26957919002393,
"count": 466132,
"is_parallel": true,
"self": 58.26957919002393
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 514.3220130569284,
"count": 233067,
"self": 7.405514097894866,
"children": {
"process_trajectory": {
"total": 184.65613563603233,
"count": 233067,
"self": 183.34558811703278,
"children": {
"RLTrainer._checkpoint": {
"total": 1.310547518999556,
"count": 10,
"self": 1.310547518999556
}
}
},
"_update_policy": {
"total": 322.26036332300123,
"count": 97,
"self": 254.6178619720073,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.64250135099394,
"count": 2910,
"self": 67.64250135099394
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.819997674436308e-07,
"count": 1,
"self": 8.819997674436308e-07
},
"TrainerController._save_models": {
"total": 0.13647037800001272,
"count": 1,
"self": 0.001992207000057533,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13447817099995518,
"count": 1,
"self": 0.13447817099995518
}
}
}
}
}
}
}