ppo-Huggy / run_logs /timers.json
RafaelJaime's picture
Huggy
ce6928a verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4098317623138428,
"min": 1.4098317623138428,
"max": 1.430120825767517,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70309.71875,
"min": 68440.0078125,
"max": 77499.171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 100.5314401622718,
"min": 92.80675422138837,
"max": 425.14406779661016,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49562.0,
"min": 48791.0,
"max": 50270.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999998.0,
"min": 49961.0,
"max": 1999998.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999998.0,
"min": 49961.0,
"max": 1999998.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3258190155029297,
"min": 0.12278978526592255,
"max": 2.4044721126556396,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1146.6287841796875,
"min": 14.36640453338623,
"max": 1255.76611328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6656382151597895,
"min": 1.9786838991010292,
"max": 3.888687462659226,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1807.1596400737762,
"min": 231.5060161948204,
"max": 1989.7611742019653,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6656382151597895,
"min": 1.9786838991010292,
"max": 3.888687462659226,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1807.1596400737762,
"min": 231.5060161948204,
"max": 1989.7611742019653,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01628740499096845,
"min": 0.01215850714749346,
"max": 0.02084824447447318,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0325748099819369,
"min": 0.02431701429498692,
"max": 0.06254473342341954,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05564994147668283,
"min": 0.021403185185045005,
"max": 0.0642728729173541,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.11129988295336565,
"min": 0.04280637037009001,
"max": 0.1916119698435068,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.591448469550015e-06,
"min": 4.591448469550015e-06,
"max": 0.00029535952654682505,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.18289693910003e-06,
"min": 9.18289693910003e-06,
"max": 0.00084380326873225,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10153045000000002,
"min": 0.10153045000000002,
"max": 0.19845317500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20306090000000004,
"min": 0.20306090000000004,
"max": 0.5812677499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.636945500000028e-05,
"min": 8.636945500000028e-05,
"max": 0.004922813432499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017273891000000056,
"min": 0.00017273891000000056,
"max": 0.014065260725,
"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": "1733393291",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "1733395802"
},
"total": 2510.6639930519996,
"count": 1,
"self": 0.47782911999956923,
"children": {
"run_training.setup": {
"total": 0.056557761000021856,
"count": 1,
"self": 0.056557761000021856
},
"TrainerController.start_learning": {
"total": 2510.129606171,
"count": 1,
"self": 4.532967059981729,
"children": {
"TrainerController._reset_env": {
"total": 5.016669700999955,
"count": 1,
"self": 5.016669700999955
},
"TrainerController.advance": {
"total": 2500.4614008850185,
"count": 231107,
"self": 4.738168276072429,
"children": {
"env_step": {
"total": 1990.7123300310109,
"count": 231107,
"self": 1561.9094149871207,
"children": {
"SubprocessEnvManager._take_step": {
"total": 425.8730847129118,
"count": 231107,
"self": 15.966307231785095,
"children": {
"TorchPolicy.evaluate": {
"total": 409.9067774811267,
"count": 222920,
"self": 409.9067774811267
}
}
},
"workers": {
"total": 2.9298303309783478,
"count": 231107,
"self": 0.0,
"children": {
"worker_root": {
"total": 2502.552651938947,
"count": 231107,
"is_parallel": true,
"self": 1235.6713950560277,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008824150002055831,
"count": 1,
"is_parallel": true,
"self": 0.00027228399994783103,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000610131000257752,
"count": 2,
"is_parallel": true,
"self": 0.000610131000257752
}
}
},
"UnityEnvironment.step": {
"total": 0.029785486000037054,
"count": 1,
"is_parallel": true,
"self": 0.00039440299974558,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019121800005450496,
"count": 1,
"is_parallel": true,
"self": 0.00019121800005450496
},
"communicator.exchange": {
"total": 0.028437000000167245,
"count": 1,
"is_parallel": true,
"self": 0.028437000000167245
},
"steps_from_proto": {
"total": 0.0007628650000697235,
"count": 1,
"is_parallel": true,
"self": 0.00021280000009937794,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005500649999703455,
"count": 2,
"is_parallel": true,
"self": 0.0005500649999703455
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1266.8812568829192,
"count": 231106,
"is_parallel": true,
"self": 37.768219277962544,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.73814051095451,
"count": 231106,
"is_parallel": true,
"self": 85.73814051095451
},
"communicator.exchange": {
"total": 1052.389859388047,
"count": 231106,
"is_parallel": true,
"self": 1052.389859388047
},
"steps_from_proto": {
"total": 90.98503770595516,
"count": 231106,
"is_parallel": true,
"self": 34.457412586073815,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.52762511988135,
"count": 462212,
"is_parallel": true,
"self": 56.52762511988135
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 505.010902577935,
"count": 231107,
"self": 7.052728051879967,
"children": {
"process_trajectory": {
"total": 166.8646389840569,
"count": 231107,
"self": 165.56970799405713,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2949309899997843,
"count": 10,
"self": 1.2949309899997843
}
}
},
"_update_policy": {
"total": 331.0935355419981,
"count": 96,
"self": 265.1320716200062,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.96146392199194,
"count": 2880,
"self": 65.96146392199194
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.279997357225511e-07,
"count": 1,
"self": 9.279997357225511e-07
},
"TrainerController._save_models": {
"total": 0.1185675970000375,
"count": 1,
"self": 0.0034346239999649697,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11513297300007252,
"count": 1,
"self": 0.11513297300007252
}
}
}
}
}
}
}