ppo-Huggy / run_logs /timers.json
ubiest's picture
Huggy first training run
f260585
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4134467840194702,
"min": 1.413445234298706,
"max": 1.4337105751037598,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70693.5390625,
"min": 68420.84375,
"max": 79535.765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 86.50699300699301,
"min": 81.68211920529801,
"max": 427.88034188034186,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49482.0,
"min": 48740.0,
"max": 50153.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999939.0,
"min": 49706.0,
"max": 1999939.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999939.0,
"min": 49706.0,
"max": 1999939.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.443744421005249,
"min": 0.1668570339679718,
"max": 2.443744421005249,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1397.82177734375,
"min": 19.35541534423828,
"max": 1456.799072265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.708593872460452,
"min": 1.7965294536331604,
"max": 3.9079296653593136,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2121.3156950473785,
"min": 208.3974166214466,
"max": 2318.44088357687,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.708593872460452,
"min": 1.7965294536331604,
"max": 3.9079296653593136,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2121.3156950473785,
"min": 208.3974166214466,
"max": 2318.44088357687,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014786747019065337,
"min": 0.013979551376542077,
"max": 0.020854113386788716,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04436024105719601,
"min": 0.028488709700104663,
"max": 0.058315774755707636,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0574962653633621,
"min": 0.02069779559969902,
"max": 0.06390711963176728,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1724887960900863,
"min": 0.04139559119939804,
"max": 0.1816470595697562,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.447298850933339e-06,
"min": 3.447298850933339e-06,
"max": 0.0002953524765491751,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0341896552800018e-05,
"min": 1.0341896552800018e-05,
"max": 0.00084401386866205,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114906666666666,
"min": 0.10114906666666666,
"max": 0.19845082500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034472,
"min": 0.20747740000000003,
"max": 0.58133795,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.733842666666677e-05,
"min": 6.733842666666677e-05,
"max": 0.004922696167500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020201528000000031,
"min": 0.00020201528000000031,
"max": 0.014068763705000003,
"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": "1671116599",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1671118840"
},
"total": 2241.3460716540003,
"count": 1,
"self": 0.4324994839998908,
"children": {
"run_training.setup": {
"total": 0.1185363120000602,
"count": 1,
"self": 0.1185363120000602
},
"TrainerController.start_learning": {
"total": 2240.795035858,
"count": 1,
"self": 3.82415752501538,
"children": {
"TrainerController._reset_env": {
"total": 10.06291604099988,
"count": 1,
"self": 10.06291604099988
},
"TrainerController.advance": {
"total": 2226.7868590669846,
"count": 232354,
"self": 3.9788792440081124,
"children": {
"env_step": {
"total": 1749.3594750920388,
"count": 232354,
"self": 1474.0556120972117,
"children": {
"SubprocessEnvManager._take_step": {
"total": 272.69967106896274,
"count": 232354,
"self": 14.137059126998338,
"children": {
"TorchPolicy.evaluate": {
"total": 258.5626119419644,
"count": 222909,
"self": 64.76218128494747,
"children": {
"TorchPolicy.sample_actions": {
"total": 193.80043065701693,
"count": 222909,
"self": 193.80043065701693
}
}
}
}
},
"workers": {
"total": 2.60419192586437,
"count": 232354,
"self": 0.0,
"children": {
"worker_root": {
"total": 2233.087992616058,
"count": 232354,
"is_parallel": true,
"self": 1018.201836721028,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00682895699992514,
"count": 1,
"is_parallel": true,
"self": 0.00030922299993108027,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0065197339999940596,
"count": 2,
"is_parallel": true,
"self": 0.0065197339999940596
}
}
},
"UnityEnvironment.step": {
"total": 0.02996741399988423,
"count": 1,
"is_parallel": true,
"self": 0.0002974770000037097,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019481100002849416,
"count": 1,
"is_parallel": true,
"self": 0.00019481100002849416
},
"communicator.exchange": {
"total": 0.028712990000030914,
"count": 1,
"is_parallel": true,
"self": 0.028712990000030914
},
"steps_from_proto": {
"total": 0.0007621359998211119,
"count": 1,
"is_parallel": true,
"self": 0.0002457999999023741,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005163359999187378,
"count": 2,
"is_parallel": true,
"self": 0.0005163359999187378
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1214.8861558950298,
"count": 232353,
"is_parallel": true,
"self": 35.05412093398513,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.29585395602498,
"count": 232353,
"is_parallel": true,
"self": 78.29585395602498
},
"communicator.exchange": {
"total": 1007.1976168540318,
"count": 232353,
"is_parallel": true,
"self": 1007.1976168540318
},
"steps_from_proto": {
"total": 94.33856415098785,
"count": 232353,
"is_parallel": true,
"self": 38.757196084075076,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.58136806691277,
"count": 464706,
"is_parallel": true,
"self": 55.58136806691277
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 473.4485047309379,
"count": 232354,
"self": 5.977921536969461,
"children": {
"process_trajectory": {
"total": 146.5818321999668,
"count": 232354,
"self": 145.3583717779668,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2234604220000165,
"count": 10,
"self": 1.2234604220000165
}
}
},
"_update_policy": {
"total": 320.8887509940016,
"count": 97,
"self": 267.39502894698853,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.49372204701308,
"count": 2910,
"self": 53.49372204701308
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.100000741251279e-07,
"count": 1,
"self": 8.100000741251279e-07
},
"TrainerController._save_models": {
"total": 0.12110241500022312,
"count": 1,
"self": 0.002863212000193016,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1182392030000301,
"count": 1,
"self": 0.1182392030000301
}
}
}
}
}
}
}