ppo-Huggy / run_logs /timers.json
danil-kuk's picture
Huggy
de5024c verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.401384711265564,
"min": 1.401384711265564,
"max": 1.4294248819351196,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70468.6328125,
"min": 68024.7265625,
"max": 78615.578125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 88.70363636363636,
"min": 82.57859531772576,
"max": 395.26771653543307,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48787.0,
"min": 48787.0,
"max": 50199.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999928.0,
"min": 49646.0,
"max": 1999928.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999928.0,
"min": 49646.0,
"max": 1999928.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.46496844291687,
"min": 0.08770405501127243,
"max": 2.46496844291687,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1355.732666015625,
"min": 11.050710678100586,
"max": 1397.135498046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7933500003814697,
"min": 1.7996368314775208,
"max": 3.9028753487529904,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2086.3425002098083,
"min": 226.75424076616764,
"max": 2146.3605912327766,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7933500003814697,
"min": 1.7996368314775208,
"max": 3.9028753487529904,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2086.3425002098083,
"min": 226.75424076616764,
"max": 2146.3605912327766,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017371340604828825,
"min": 0.01277637030070764,
"max": 0.02066538825990089,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.052114021814486475,
"min": 0.02555274060141528,
"max": 0.059646929847561606,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0529004701309734,
"min": 0.0209927247526745,
"max": 0.0629064486672481,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15870141039292018,
"min": 0.041985449505349,
"max": 0.18871934600174428,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.1405989531666694e-06,
"min": 3.1405989531666694e-06,
"max": 0.00029533845155384995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.421796859500008e-06,
"min": 9.421796859500008e-06,
"max": 0.0008439163686945499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10104683333333336,
"min": 0.10104683333333336,
"max": 0.19844615000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3031405000000001,
"min": 0.20725155000000003,
"max": 0.5813054500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.223698333333337e-05,
"min": 6.223698333333337e-05,
"max": 0.004922462884999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001867109500000001,
"min": 0.0001867109500000001,
"max": 0.014067141955000001,
"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": "1739693042",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739695518"
},
"total": 2475.777025405,
"count": 1,
"self": 0.441949551000107,
"children": {
"run_training.setup": {
"total": 0.02217420499994205,
"count": 1,
"self": 0.02217420499994205
},
"TrainerController.start_learning": {
"total": 2475.312901649,
"count": 1,
"self": 4.499534549950113,
"children": {
"TrainerController._reset_env": {
"total": 3.378080953000108,
"count": 1,
"self": 3.378080953000108
},
"TrainerController.advance": {
"total": 2467.3216748860505,
"count": 231904,
"self": 4.973404069975459,
"children": {
"env_step": {
"total": 1976.6837692731003,
"count": 231904,
"self": 1548.2400010620509,
"children": {
"SubprocessEnvManager._take_step": {
"total": 425.7352611520304,
"count": 231904,
"self": 15.890047944019784,
"children": {
"TorchPolicy.evaluate": {
"total": 409.8452132080106,
"count": 222956,
"self": 409.8452132080106
}
}
},
"workers": {
"total": 2.7085070590189844,
"count": 231904,
"self": 0.0,
"children": {
"worker_root": {
"total": 2467.8905168019833,
"count": 231904,
"is_parallel": true,
"self": 1205.4140582159876,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001088702999936686,
"count": 1,
"is_parallel": true,
"self": 0.00036306099991634255,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007256420000203434,
"count": 2,
"is_parallel": true,
"self": 0.0007256420000203434
}
}
},
"UnityEnvironment.step": {
"total": 0.029561079000018253,
"count": 1,
"is_parallel": true,
"self": 0.0003338239998811332,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019600400003128016,
"count": 1,
"is_parallel": true,
"self": 0.00019600400003128016
},
"communicator.exchange": {
"total": 0.02833718300007604,
"count": 1,
"is_parallel": true,
"self": 0.02833718300007604
},
"steps_from_proto": {
"total": 0.0006940680000298016,
"count": 1,
"is_parallel": true,
"self": 0.00018238300003758923,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005116849999922124,
"count": 2,
"is_parallel": true,
"self": 0.0005116849999922124
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1262.4764585859957,
"count": 231903,
"is_parallel": true,
"self": 37.93749306483505,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.9718432700596,
"count": 231903,
"is_parallel": true,
"self": 81.9718432700596
},
"communicator.exchange": {
"total": 1053.7210973820534,
"count": 231903,
"is_parallel": true,
"self": 1053.7210973820534
},
"steps_from_proto": {
"total": 88.84602486904748,
"count": 231903,
"is_parallel": true,
"self": 32.70571898106425,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.14030588798323,
"count": 463806,
"is_parallel": true,
"self": 56.14030588798323
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 485.6645015429748,
"count": 231904,
"self": 6.767458174900071,
"children": {
"process_trajectory": {
"total": 162.82854772907467,
"count": 231904,
"self": 161.4492164850742,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3793312440004684,
"count": 10,
"self": 1.3793312440004684
}
}
},
"_update_policy": {
"total": 316.06849563900005,
"count": 97,
"self": 251.45185412699334,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.61664151200671,
"count": 2910,
"self": 64.61664151200671
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.900001375877764e-07,
"count": 1,
"self": 8.900001375877764e-07
},
"TrainerController._save_models": {
"total": 0.11361036999960561,
"count": 1,
"self": 0.0019651279999379767,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11164524199966763,
"count": 1,
"self": 0.11164524199966763
}
}
}
}
}
}
}