ppo-Huggy / run_logs /timers.json
kavmal7's picture
Dog done
12edd0b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3976579904556274,
"min": 1.3976579904556274,
"max": 1.4292244911193848,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70905.984375,
"min": 68696.78125,
"max": 76622.296875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 111.7437641723356,
"min": 98.87225548902195,
"max": 422.890756302521,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49279.0,
"min": 48839.0,
"max": 50324.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999957.0,
"min": 49890.0,
"max": 1999957.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999957.0,
"min": 49890.0,
"max": 1999957.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3461034297943115,
"min": -0.022013112902641296,
"max": 2.387450695037842,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1034.631591796875,
"min": -2.5975472927093506,
"max": 1146.08447265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6200971354702975,
"min": 1.8334133279020504,
"max": 3.738685535903696,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1596.4628367424011,
"min": 216.34277269244194,
"max": 1819.0280629992485,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6200971354702975,
"min": 1.8334133279020504,
"max": 3.738685535903696,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1596.4628367424011,
"min": 216.34277269244194,
"max": 1819.0280629992485,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015079839803123225,
"min": 0.013303537648526901,
"max": 0.01939769200544106,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03015967960624645,
"min": 0.02860472583367179,
"max": 0.05248594781393573,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.051466230365137255,
"min": 0.023668879705170794,
"max": 0.06403087576230368,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10293246073027451,
"min": 0.04733775941034159,
"max": 0.18579106989006203,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.461773512774993e-06,
"min": 4.461773512774993e-06,
"max": 0.0002953329015556999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.923547025549985e-06,
"min": 8.923547025549985e-06,
"max": 0.0008442592685802496,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10148722500000001,
"min": 0.10148722500000001,
"max": 0.19844429999999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20297445000000003,
"min": 0.20297445000000003,
"max": 0.5814197500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.42125274999999e-05,
"min": 8.42125274999999e-05,
"max": 0.004922370569999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001684250549999998,
"min": 0.0001684250549999998,
"max": 0.014072845525000002,
"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": "1731796317",
"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": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1731798816"
},
"total": 2498.8040203250002,
"count": 1,
"self": 0.42559492100008356,
"children": {
"run_training.setup": {
"total": 0.0553438270001152,
"count": 1,
"self": 0.0553438270001152
},
"TrainerController.start_learning": {
"total": 2498.3230815770003,
"count": 1,
"self": 4.4170728508916,
"children": {
"TrainerController._reset_env": {
"total": 5.682169505999809,
"count": 1,
"self": 5.682169505999809
},
"TrainerController.advance": {
"total": 2488.1078004381097,
"count": 230950,
"self": 4.76446186209796,
"children": {
"env_step": {
"total": 1977.6045996610753,
"count": 230950,
"self": 1550.983443134864,
"children": {
"SubprocessEnvManager._take_step": {
"total": 423.8428311290529,
"count": 230950,
"self": 15.969110652149084,
"children": {
"TorchPolicy.evaluate": {
"total": 407.8737204769038,
"count": 222992,
"self": 407.8737204769038
}
}
},
"workers": {
"total": 2.778325397158369,
"count": 230950,
"self": 0.0,
"children": {
"worker_root": {
"total": 2490.8092676798005,
"count": 230950,
"is_parallel": true,
"self": 1229.9046852659224,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008914749998893967,
"count": 1,
"is_parallel": true,
"self": 0.0002523519997339463,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006391230001554504,
"count": 2,
"is_parallel": true,
"self": 0.0006391230001554504
}
}
},
"UnityEnvironment.step": {
"total": 0.02942188899987741,
"count": 1,
"is_parallel": true,
"self": 0.00039123099963944696,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019641100016087876,
"count": 1,
"is_parallel": true,
"self": 0.00019641100016087876
},
"communicator.exchange": {
"total": 0.028066949000049135,
"count": 1,
"is_parallel": true,
"self": 0.028066949000049135
},
"steps_from_proto": {
"total": 0.0007672980000279495,
"count": 1,
"is_parallel": true,
"self": 0.0002157070000521344,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005515909999758151,
"count": 2,
"is_parallel": true,
"self": 0.0005515909999758151
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1260.9045824138782,
"count": 230949,
"is_parallel": true,
"self": 37.694070730810836,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.07312504290189,
"count": 230949,
"is_parallel": true,
"self": 84.07312504290189
},
"communicator.exchange": {
"total": 1048.2438671460754,
"count": 230949,
"is_parallel": true,
"self": 1048.2438671460754
},
"steps_from_proto": {
"total": 90.89351949409001,
"count": 230949,
"is_parallel": true,
"self": 34.50305205515724,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.390467438932774,
"count": 461898,
"is_parallel": true,
"self": 56.390467438932774
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 505.7387389149367,
"count": 230950,
"self": 6.73502046096155,
"children": {
"process_trajectory": {
"total": 161.72296399797688,
"count": 230950,
"self": 160.3223369689763,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4006270290005887,
"count": 10,
"self": 1.4006270290005887
}
}
},
"_update_policy": {
"total": 337.28075445599825,
"count": 96,
"self": 271.0373095629898,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.24344489300847,
"count": 2880,
"self": 66.24344489300847
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.339999471383635e-06,
"count": 1,
"self": 1.339999471383635e-06
},
"TrainerController._save_models": {
"total": 0.11603744199965149,
"count": 1,
"self": 0.002021698999669752,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11401574299998174,
"count": 1,
"self": 0.11401574299998174
}
}
}
}
}
}
}