ppo-Huggy / run_logs /timers.json
csabazs's picture
Huggy
33f6775 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3986241817474365,
"min": 1.3986241817474365,
"max": 1.4249529838562012,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69492.0390625,
"min": 68915.921875,
"max": 76766.3984375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.97712418300654,
"min": 73.82485029940119,
"max": 351.5774647887324,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49558.0,
"min": 49016.0,
"max": 49924.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999508.0,
"min": 49967.0,
"max": 1999508.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999508.0,
"min": 49967.0,
"max": 1999508.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4411814212799072,
"min": 0.09124316275119781,
"max": 2.52083158493042,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1494.0030517578125,
"min": 12.865285873413086,
"max": 1650.578125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.770094389814177,
"min": 1.6304912089456058,
"max": 4.0632037798695215,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2307.2977665662766,
"min": 229.8992604613304,
"max": 2592.798264980316,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.770094389814177,
"min": 1.6304912089456058,
"max": 4.0632037798695215,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2307.2977665662766,
"min": 229.8992604613304,
"max": 2592.798264980316,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01709876670275763,
"min": 0.01365286419337887,
"max": 0.019432116836671617,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.051296300108272894,
"min": 0.02730572838675774,
"max": 0.05829635051001485,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05874722980790668,
"min": 0.024547127665330966,
"max": 0.06381370106505023,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17624168942372004,
"min": 0.04909425533066193,
"max": 0.19144110319515067,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7999487333833268e-06,
"min": 3.7999487333833268e-06,
"max": 0.00029532562655812497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.139984620014998e-05,
"min": 1.139984620014998e-05,
"max": 0.0008440369686543499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10126661666666666,
"min": 0.10126661666666666,
"max": 0.19844187500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30379985,
"min": 0.20766144999999997,
"max": 0.5813456499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.320417166666657e-05,
"min": 7.320417166666657e-05,
"max": 0.0049222495625,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002196125149999997,
"min": 0.0002196125149999997,
"max": 0.014069147934999998,
"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": "1733996986",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1733999463"
},
"total": 2477.314483465,
"count": 1,
"self": 0.4254540690003523,
"children": {
"run_training.setup": {
"total": 0.05756518399994093,
"count": 1,
"self": 0.05756518399994093
},
"TrainerController.start_learning": {
"total": 2476.831464212,
"count": 1,
"self": 4.4486786500283415,
"children": {
"TrainerController._reset_env": {
"total": 4.9033292040001015,
"count": 1,
"self": 4.9033292040001015
},
"TrainerController.advance": {
"total": 2467.3694067309707,
"count": 233200,
"self": 4.703371959820743,
"children": {
"env_step": {
"total": 1948.7283072840662,
"count": 233200,
"self": 1535.3842592931749,
"children": {
"SubprocessEnvManager._take_step": {
"total": 410.5587068359491,
"count": 233200,
"self": 15.658995378011696,
"children": {
"TorchPolicy.evaluate": {
"total": 394.8997114579374,
"count": 222932,
"self": 394.8997114579374
}
}
},
"workers": {
"total": 2.7853411549422162,
"count": 233200,
"self": 0.0,
"children": {
"worker_root": {
"total": 2469.1515684760507,
"count": 233200,
"is_parallel": true,
"self": 1221.0197433560857,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008451070000319305,
"count": 1,
"is_parallel": true,
"self": 0.00026210299984086305,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005830040001910675,
"count": 2,
"is_parallel": true,
"self": 0.0005830040001910675
}
}
},
"UnityEnvironment.step": {
"total": 0.030125059000056353,
"count": 1,
"is_parallel": true,
"self": 0.0003804510001828021,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002029209999818704,
"count": 1,
"is_parallel": true,
"self": 0.0002029209999818704
},
"communicator.exchange": {
"total": 0.028732087999969735,
"count": 1,
"is_parallel": true,
"self": 0.028732087999969735
},
"steps_from_proto": {
"total": 0.0008095989999219455,
"count": 1,
"is_parallel": true,
"self": 0.00023920099988572474,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005703980000362208,
"count": 2,
"is_parallel": true,
"self": 0.0005703980000362208
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1248.131825119965,
"count": 233199,
"is_parallel": true,
"self": 37.3640520339618,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.59408767591094,
"count": 233199,
"is_parallel": true,
"self": 82.59408767591094
},
"communicator.exchange": {
"total": 1038.583312970051,
"count": 233199,
"is_parallel": true,
"self": 1038.583312970051
},
"steps_from_proto": {
"total": 89.59037244004116,
"count": 233199,
"is_parallel": true,
"self": 33.683675516030235,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.90669692401093,
"count": 466398,
"is_parallel": true,
"self": 55.90669692401093
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 513.9377274870837,
"count": 233200,
"self": 6.314723999154012,
"children": {
"process_trajectory": {
"total": 175.8795995559301,
"count": 233200,
"self": 174.61597372193046,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2636258339996402,
"count": 10,
"self": 1.2636258339996402
}
}
},
"_update_policy": {
"total": 331.74340393199964,
"count": 97,
"self": 265.9761550099929,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.76724892200673,
"count": 2910,
"self": 65.76724892200673
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.76000137598021e-07,
"count": 1,
"self": 9.76000137598021e-07
},
"TrainerController._save_models": {
"total": 0.11004865100039751,
"count": 1,
"self": 0.0021153110005798226,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10793333999981769,
"count": 1,
"self": 0.10793333999981769
}
}
}
}
}
}
}