ppo-Huggy / run_logs /timers.json
CreativeEvolution's picture
Huggy first training
d7374b5
raw
history blame
17.9 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4106980562210083,
"min": 1.4106980562210083,
"max": 1.4314528703689575,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71492.765625,
"min": 69059.984375,
"max": 77831.0,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 93.21072796934865,
"min": 86.25305410122164,
"max": 399.472,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48656.0,
"min": 48656.0,
"max": 50237.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999931.0,
"min": 49352.0,
"max": 1999931.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999931.0,
"min": 49352.0,
"max": 1999931.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.395909309387207,
"min": 0.07087629288434982,
"max": 2.44598388671875,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1253.060546875,
"min": 8.788660049438477,
"max": 1375.0291748046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6878150071286333,
"min": 1.7826218343069475,
"max": 3.886596786140932,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1928.7272487282753,
"min": 221.0451074540615,
"max": 2154.35086029768,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6878150071286333,
"min": 1.7826218343069475,
"max": 3.886596786140932,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1928.7272487282753,
"min": 221.0451074540615,
"max": 2154.35086029768,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016319106391488782,
"min": 0.014737971860288074,
"max": 0.019867653902717088,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04895731917446634,
"min": 0.030304068304758403,
"max": 0.05566421156666669,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.056076694114340665,
"min": 0.02065454513455431,
"max": 0.06024209068467219,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.168230082343022,
"min": 0.04130909026910862,
"max": 0.18065017499029637,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4407488531166674e-06,
"min": 3.4407488531166674e-06,
"max": 0.000295363726545425,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0322246559350003e-05,
"min": 1.0322246559350003e-05,
"max": 0.00084419176860275,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114688333333333,
"min": 0.10114688333333333,
"max": 0.198454575,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30344065,
"min": 0.20743134999999996,
"max": 0.5813972499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.722947833333335e-05,
"min": 6.722947833333335e-05,
"max": 0.004922883292499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020168843500000008,
"min": 0.00020168843500000008,
"max": 0.014071722775,
"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": "1670659645",
"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": "1670661894"
},
"total": 2248.6601040899995,
"count": 1,
"self": 0.3973864199997479,
"children": {
"run_training.setup": {
"total": 0.10391982499993446,
"count": 1,
"self": 0.10391982499993446
},
"TrainerController.start_learning": {
"total": 2248.1587978449998,
"count": 1,
"self": 3.9340872079715155,
"children": {
"TrainerController._reset_env": {
"total": 10.858998750000069,
"count": 1,
"self": 10.858998750000069
},
"TrainerController.advance": {
"total": 2233.2525818000286,
"count": 232212,
"self": 4.029358244982177,
"children": {
"env_step": {
"total": 1759.4907451440884,
"count": 232212,
"self": 1476.4426561579985,
"children": {
"SubprocessEnvManager._take_step": {
"total": 280.31763042400917,
"count": 232212,
"self": 14.718866049061035,
"children": {
"TorchPolicy.evaluate": {
"total": 265.59876437494813,
"count": 223070,
"self": 66.8484688489599,
"children": {
"TorchPolicy.sample_actions": {
"total": 198.75029552598824,
"count": 223070,
"self": 198.75029552598824
}
}
}
}
},
"workers": {
"total": 2.7304585620807984,
"count": 232212,
"self": 0.0,
"children": {
"worker_root": {
"total": 2240.108677996002,
"count": 232212,
"is_parallel": true,
"self": 1030.3202316460015,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021478439999782495,
"count": 1,
"is_parallel": true,
"self": 0.0003821580000931135,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001765685999885136,
"count": 2,
"is_parallel": true,
"self": 0.001765685999885136
}
}
},
"UnityEnvironment.step": {
"total": 0.02975689900006273,
"count": 1,
"is_parallel": true,
"self": 0.00029804699988744687,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018392900005892443,
"count": 1,
"is_parallel": true,
"self": 0.00018392900005892443
},
"communicator.exchange": {
"total": 0.02840458400009993,
"count": 1,
"is_parallel": true,
"self": 0.02840458400009993
},
"steps_from_proto": {
"total": 0.000870339000016429,
"count": 1,
"is_parallel": true,
"self": 0.00030846899994685373,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005618700000695753,
"count": 2,
"is_parallel": true,
"self": 0.0005618700000695753
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1209.7884463500004,
"count": 232211,
"is_parallel": true,
"self": 34.19236594114386,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.39835732001006,
"count": 232211,
"is_parallel": true,
"self": 76.39835732001006
},
"communicator.exchange": {
"total": 1005.2515169268981,
"count": 232211,
"is_parallel": true,
"self": 1005.2515169268981
},
"steps_from_proto": {
"total": 93.94620616194834,
"count": 232211,
"is_parallel": true,
"self": 40.34599923993687,
"children": {
"_process_rank_one_or_two_observation": {
"total": 53.600206922011466,
"count": 464422,
"is_parallel": true,
"self": 53.600206922011466
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 469.7324784109578,
"count": 232212,
"self": 6.25496060399405,
"children": {
"process_trajectory": {
"total": 148.98979275296426,
"count": 232212,
"self": 148.4620007409643,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5277920119999635,
"count": 4,
"self": 0.5277920119999635
}
}
},
"_update_policy": {
"total": 314.4877250539995,
"count": 97,
"self": 260.78478611799676,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.70293893600274,
"count": 2910,
"self": 53.70293893600274
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.669999260746408e-07,
"count": 1,
"self": 8.669999260746408e-07
},
"TrainerController._save_models": {
"total": 0.11312921999979153,
"count": 1,
"self": 0.002010371999858762,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11111884799993277,
"count": 1,
"self": 0.11111884799993277
}
}
}
}
}
}
}