ppo-Huggy / run_logs /timers.json
YoungMeng's picture
Huggy
cca3f71
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4071804285049438,
"min": 1.4071804285049438,
"max": 1.4286656379699707,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71294.796875,
"min": 68423.390625,
"max": 77625.953125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 122.22439024390243,
"min": 89.72958257713249,
"max": 376.94736842105266,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50112.0,
"min": 49101.0,
"max": 50134.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999800.0,
"min": 49804.0,
"max": 1999800.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999800.0,
"min": 49804.0,
"max": 1999800.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3269460201263428,
"min": 0.05282894894480705,
"max": 2.408529758453369,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 954.0478515625,
"min": 6.973421096801758,
"max": 1309.6319580078125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4067735731601716,
"min": 1.8071273147608296,
"max": 3.9517044430971144,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1396.7771649956703,
"min": 238.5408055484295,
"max": 2045.604074895382,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4067735731601716,
"min": 1.8071273147608296,
"max": 3.9517044430971144,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1396.7771649956703,
"min": 238.5408055484295,
"max": 2045.604074895382,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016370479964340726,
"min": 0.013303645277725689,
"max": 0.01889237828581827,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03274095992868145,
"min": 0.026607290555451378,
"max": 0.056677134857454806,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.03889215895906091,
"min": 0.023469230315337576,
"max": 0.06304103198150793,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.07778431791812182,
"min": 0.04693846063067515,
"max": 0.17837516876558462,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.4391985203000025e-06,
"min": 4.4391985203000025e-06,
"max": 0.0002952912015696,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.878397040600005e-06,
"min": 8.878397040600005e-06,
"max": 0.0008439397686867498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10147970000000002,
"min": 0.10147970000000002,
"max": 0.19843039999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20295940000000004,
"min": 0.20295940000000004,
"max": 0.58131325,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.383703000000002e-05,
"min": 8.383703000000002e-05,
"max": 0.004921676960000002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016767406000000004,
"min": 0.00016767406000000004,
"max": 0.014067531175000002,
"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": "1696523166",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1696525766"
},
"total": 2599.628253769,
"count": 1,
"self": 0.4479467589999331,
"children": {
"run_training.setup": {
"total": 0.049267030999999406,
"count": 1,
"self": 0.049267030999999406
},
"TrainerController.start_learning": {
"total": 2599.131039979,
"count": 1,
"self": 4.858777621880108,
"children": {
"TrainerController._reset_env": {
"total": 5.014500656999985,
"count": 1,
"self": 5.014500656999985
},
"TrainerController.advance": {
"total": 2589.1331596021196,
"count": 231254,
"self": 4.806796721166847,
"children": {
"env_step": {
"total": 2020.9407378820308,
"count": 231254,
"self": 1704.3740157730272,
"children": {
"SubprocessEnvManager._take_step": {
"total": 313.4141088539963,
"count": 231254,
"self": 17.7818192510141,
"children": {
"TorchPolicy.evaluate": {
"total": 295.6322896029822,
"count": 223136,
"self": 295.6322896029822
}
}
},
"workers": {
"total": 3.1526132550072816,
"count": 231254,
"self": 0.0,
"children": {
"worker_root": {
"total": 2590.9473089678913,
"count": 231254,
"is_parallel": true,
"self": 1199.0211835868345,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009703359999662098,
"count": 1,
"is_parallel": true,
"self": 0.00026732599997103534,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007030099999951744,
"count": 2,
"is_parallel": true,
"self": 0.0007030099999951744
}
}
},
"UnityEnvironment.step": {
"total": 0.05178063199997496,
"count": 1,
"is_parallel": true,
"self": 0.0005200580000064292,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002720599999861406,
"count": 1,
"is_parallel": true,
"self": 0.0002720599999861406
},
"communicator.exchange": {
"total": 0.05006959199999983,
"count": 1,
"is_parallel": true,
"self": 0.05006959199999983
},
"steps_from_proto": {
"total": 0.0009189219999825582,
"count": 1,
"is_parallel": true,
"self": 0.000365387999977429,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005535340000051292,
"count": 2,
"is_parallel": true,
"self": 0.0005535340000051292
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1391.9261253810569,
"count": 231253,
"is_parallel": true,
"self": 41.86941536208906,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 89.07419142098894,
"count": 231253,
"is_parallel": true,
"self": 89.07419142098894
},
"communicator.exchange": {
"total": 1155.8831385259746,
"count": 231253,
"is_parallel": true,
"self": 1155.8831385259746
},
"steps_from_proto": {
"total": 105.0993800720043,
"count": 231253,
"is_parallel": true,
"self": 39.749996452943776,
"children": {
"_process_rank_one_or_two_observation": {
"total": 65.34938361906052,
"count": 462506,
"is_parallel": true,
"self": 65.34938361906052
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 563.3856249989221,
"count": 231254,
"self": 7.215411914932247,
"children": {
"process_trajectory": {
"total": 144.1010865319908,
"count": 231254,
"self": 142.80474495699087,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2963415749999285,
"count": 10,
"self": 1.2963415749999285
}
}
},
"_update_policy": {
"total": 412.06912655199915,
"count": 96,
"self": 350.9673325799838,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.101793972015344,
"count": 2880,
"self": 61.101793972015344
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.780001164472196e-07,
"count": 1,
"self": 9.780001164472196e-07
},
"TrainerController._save_models": {
"total": 0.12460112000007939,
"count": 1,
"self": 0.002115838999998232,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12248528100008116,
"count": 1,
"self": 0.12248528100008116
}
}
}
}
}
}
}