ppo-Huggy / run_logs /timers.json
HugeFighter's picture
Huggy
a317919 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4050055742263794,
"min": 1.4050055742263794,
"max": 1.4287430047988892,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70282.59375,
"min": 68043.28125,
"max": 76602.8125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 105.09766454352442,
"min": 86.82570422535211,
"max": 419.672268907563,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49501.0,
"min": 48980.0,
"max": 50211.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999988.0,
"min": 49687.0,
"max": 1999988.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999988.0,
"min": 49687.0,
"max": 1999988.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.330543041229248,
"min": 0.09332475811243057,
"max": 2.409088134765625,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1097.685791015625,
"min": 11.012321472167969,
"max": 1334.422119140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.472549626528584,
"min": 1.8079330836564809,
"max": 3.882534772392333,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1635.570874094963,
"min": 213.33610387146473,
"max": 2125.9502703547478,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.472549626528584,
"min": 1.8079330836564809,
"max": 3.882534772392333,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1635.570874094963,
"min": 213.33610387146473,
"max": 2125.9502703547478,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018180705491814327,
"min": 0.011989289615667077,
"max": 0.021855997273572333,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.036361410983628654,
"min": 0.023978579231334153,
"max": 0.0590100757535159,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04883846677839756,
"min": 0.021395749412477016,
"max": 0.056284309799472486,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09767693355679512,
"min": 0.04279149882495403,
"max": 0.16885292939841745,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.242548585849992e-06,
"min": 4.242548585849992e-06,
"max": 0.000295311376562875,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.485097171699983e-06,
"min": 8.485097171699983e-06,
"max": 0.0008441431686189501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10141414999999998,
"min": 0.10141414999999998,
"max": 0.19843712500000008,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20282829999999996,
"min": 0.20282829999999996,
"max": 0.5813810500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.05660849999999e-05,
"min": 8.05660849999999e-05,
"max": 0.004922012537499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001611321699999998,
"min": 0.0001611321699999998,
"max": 0.014070914395,
"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": "1735813615",
"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": "1735815989"
},
"total": 2374.007791891,
"count": 1,
"self": 0.42480256900034874,
"children": {
"run_training.setup": {
"total": 0.0565471269999307,
"count": 1,
"self": 0.0565471269999307
},
"TrainerController.start_learning": {
"total": 2373.5264421949996,
"count": 1,
"self": 4.194854779842444,
"children": {
"TrainerController._reset_env": {
"total": 5.021956991000025,
"count": 1,
"self": 5.021956991000025
},
"TrainerController.advance": {
"total": 2364.197868711157,
"count": 231494,
"self": 4.231758408035603,
"children": {
"env_step": {
"total": 1868.1408150220896,
"count": 231494,
"self": 1472.235238884122,
"children": {
"SubprocessEnvManager._take_step": {
"total": 393.2959895640138,
"count": 231494,
"self": 14.93391465797572,
"children": {
"TorchPolicy.evaluate": {
"total": 378.36207490603806,
"count": 223049,
"self": 378.36207490603806
}
}
},
"workers": {
"total": 2.6095865739537203,
"count": 231494,
"self": 0.0,
"children": {
"worker_root": {
"total": 2366.621490695922,
"count": 231494,
"is_parallel": true,
"self": 1169.4172973148422,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009483440001076815,
"count": 1,
"is_parallel": true,
"self": 0.00027386500005377457,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006744790000539069,
"count": 2,
"is_parallel": true,
"self": 0.0006744790000539069
}
}
},
"UnityEnvironment.step": {
"total": 0.06527239599995482,
"count": 1,
"is_parallel": true,
"self": 0.00035558799982027267,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018468400003257557,
"count": 1,
"is_parallel": true,
"self": 0.00018468400003257557
},
"communicator.exchange": {
"total": 0.06406222300006448,
"count": 1,
"is_parallel": true,
"self": 0.06406222300006448
},
"steps_from_proto": {
"total": 0.0006699010000374983,
"count": 1,
"is_parallel": true,
"self": 0.00017406999995728256,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004958310000802157,
"count": 2,
"is_parallel": true,
"self": 0.0004958310000802157
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1197.20419338108,
"count": 231493,
"is_parallel": true,
"self": 36.966747123066625,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.53016154402508,
"count": 231493,
"is_parallel": true,
"self": 80.53016154402508
},
"communicator.exchange": {
"total": 993.8781163799324,
"count": 231493,
"is_parallel": true,
"self": 993.8781163799324
},
"steps_from_proto": {
"total": 85.8291683340558,
"count": 231493,
"is_parallel": true,
"self": 30.177823886208216,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.65134444784758,
"count": 462986,
"is_parallel": true,
"self": 55.65134444784758
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 491.8252952810317,
"count": 231494,
"self": 6.031792291066495,
"children": {
"process_trajectory": {
"total": 155.01282651996667,
"count": 231494,
"self": 153.5985270419676,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4142994779990659,
"count": 10,
"self": 1.4142994779990659
}
}
},
"_update_policy": {
"total": 330.7806764699985,
"count": 96,
"self": 265.9094734829989,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.8712029869996,
"count": 2880,
"self": 64.8712029869996
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0680000741558615e-06,
"count": 1,
"self": 1.0680000741558615e-06
},
"TrainerController._save_models": {
"total": 0.1117606450002313,
"count": 1,
"self": 0.002047817000402574,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10971282799982873,
"count": 1,
"self": 0.10971282799982873
}
}
}
}
}
}
}