ppo-Huggy / run_logs /timers.json
Esteban00007's picture
Huggy
44f7fc8 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4054930210113525,
"min": 1.4054930210113525,
"max": 1.428471565246582,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70118.640625,
"min": 67819.09375,
"max": 78294.171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 91.75185185185185,
"min": 80.9468438538206,
"max": 369.5925925925926,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49546.0,
"min": 48730.0,
"max": 50041.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999969.0,
"min": 49280.0,
"max": 1999969.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999969.0,
"min": 49280.0,
"max": 1999969.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.44339919090271,
"min": -0.013240497559309006,
"max": 2.489198923110962,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1319.435546875,
"min": -1.7742266654968262,
"max": 1502.0537109375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8039607056864986,
"min": 1.7600808942051076,
"max": 4.0350549168211955,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2054.1387810707092,
"min": 235.85083982348442,
"max": 2412.962840259075,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8039607056864986,
"min": 1.7600808942051076,
"max": 4.0350549168211955,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2054.1387810707092,
"min": 235.85083982348442,
"max": 2412.962840259075,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01772850119644621,
"min": 0.013392449949363557,
"max": 0.020637512856774266,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05318550358933863,
"min": 0.026784899898727114,
"max": 0.059749271518133654,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.052290997778375946,
"min": 0.02262552467485269,
"max": 0.06643913617978493,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15687299333512783,
"min": 0.04525104934970538,
"max": 0.18625651163359483,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3684988772000036e-06,
"min": 3.3684988772000036e-06,
"max": 0.0002953434765521749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0105496631600011e-05,
"min": 1.0105496631600011e-05,
"max": 0.0008438206687264499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10112280000000001,
"min": 0.10112280000000001,
"max": 0.19844782499999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30336840000000004,
"min": 0.20742375000000007,
"max": 0.5812735499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.602772000000006e-05,
"min": 6.602772000000006e-05,
"max": 0.0049225464675,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001980831600000002,
"min": 0.0001980831600000002,
"max": 0.014065550145,
"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": "1733310630",
"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": "1733313785"
},
"total": 3154.166088745,
"count": 1,
"self": 0.533272212999691,
"children": {
"run_training.setup": {
"total": 0.10170063900000059,
"count": 1,
"self": 0.10170063900000059
},
"TrainerController.start_learning": {
"total": 3153.531115893,
"count": 1,
"self": 6.704089047943398,
"children": {
"TrainerController._reset_env": {
"total": 6.174844054999994,
"count": 1,
"self": 6.174844054999994
},
"TrainerController.advance": {
"total": 3140.5222219220564,
"count": 232408,
"self": 6.406675065942181,
"children": {
"env_step": {
"total": 2530.224053096068,
"count": 232408,
"self": 1988.004470347118,
"children": {
"SubprocessEnvManager._take_step": {
"total": 538.0491469879089,
"count": 232408,
"self": 21.15002855100181,
"children": {
"TorchPolicy.evaluate": {
"total": 516.8991184369071,
"count": 223002,
"self": 516.8991184369071
}
}
},
"workers": {
"total": 4.1704357610410625,
"count": 232408,
"self": 0.0,
"children": {
"worker_root": {
"total": 3143.784666899059,
"count": 232408,
"is_parallel": true,
"self": 1545.414255424063,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010002569999869593,
"count": 1,
"is_parallel": true,
"self": 0.0002943169999980455,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007059399999889138,
"count": 2,
"is_parallel": true,
"self": 0.0007059399999889138
}
}
},
"UnityEnvironment.step": {
"total": 0.0354833779999808,
"count": 1,
"is_parallel": true,
"self": 0.0004020900000796246,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002281349999293525,
"count": 1,
"is_parallel": true,
"self": 0.0002281349999293525
},
"communicator.exchange": {
"total": 0.03403217200002473,
"count": 1,
"is_parallel": true,
"self": 0.03403217200002473
},
"steps_from_proto": {
"total": 0.0008209809999470963,
"count": 1,
"is_parallel": true,
"self": 0.0002242260000002716,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005967549999468247,
"count": 2,
"is_parallel": true,
"self": 0.0005967549999468247
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1598.3704114749962,
"count": 232407,
"is_parallel": true,
"self": 46.57850001284896,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 102.0101080580256,
"count": 232407,
"is_parallel": true,
"self": 102.0101080580256
},
"communicator.exchange": {
"total": 1335.6309191251949,
"count": 232407,
"is_parallel": true,
"self": 1335.6309191251949
},
"steps_from_proto": {
"total": 114.1508842789267,
"count": 232407,
"is_parallel": true,
"self": 42.213134328833235,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.93774995009346,
"count": 464814,
"is_parallel": true,
"self": 71.93774995009346
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 603.8914937600463,
"count": 232408,
"self": 9.674662026964597,
"children": {
"process_trajectory": {
"total": 213.9947213330821,
"count": 232408,
"self": 212.446220924082,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5485004090000984,
"count": 10,
"self": 1.5485004090000984
}
}
},
"_update_policy": {
"total": 380.22211039999956,
"count": 97,
"self": 305.22628925999754,
"children": {
"TorchPPOOptimizer.update": {
"total": 74.99582114000202,
"count": 2910,
"self": 74.99582114000202
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0759999895526562e-06,
"count": 1,
"self": 1.0759999895526562e-06
},
"TrainerController._save_models": {
"total": 0.12995979200013608,
"count": 1,
"self": 0.002444803000344109,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12751498899979197,
"count": 1,
"self": 0.12751498899979197
}
}
}
}
}
}
}