ppo-Huggy / run_logs /timers.json
dragiychev's picture
Huggy
f055ee4 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.0750551223754883,
"min": 1.0750551223754883,
"max": 1.4274494647979736,
"count": 120
},
"Huggy.Policy.Entropy.sum": {
"value": 26497.958984375,
"min": 26194.76953125,
"max": 39724.59765625,
"count": 120
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 136.15083798882682,
"min": 95.97165991902834,
"max": 397.65,
"count": 120
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 24371.0,
"min": 23347.0,
"max": 26153.0,
"count": 120
},
"Huggy.Step.mean": {
"value": 2999569.0,
"min": 24708.0,
"max": 2999569.0,
"count": 120
},
"Huggy.Step.sum": {
"value": 2999569.0,
"min": 24708.0,
"max": 2999569.0,
"count": 120
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 1.620908498764038,
"min": 0.0003112278354819864,
"max": 1.9100748300552368,
"count": 120
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 320.93988037109375,
"min": 0.026454366743564606,
"max": 489.4862365722656,
"count": 120
},
"Huggy.Policy.CuriosityValueEstimate.mean": {
"value": 0.6212010383605957,
"min": -0.03141486272215843,
"max": 1.3411234617233276,
"count": 120
},
"Huggy.Policy.CuriosityValueEstimate.sum": {
"value": 122.997802734375,
"min": -2.5131890773773193,
"max": 187.8009033203125,
"count": 120
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 2.8292304856909647,
"min": 1.536363914143294,
"max": 3.974376110434532,
"count": 120
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 509.2614874243736,
"min": 98.32729050517082,
"max": 935.9394870996475,
"count": 120
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 2.8292304856909647,
"min": 1.536363914143294,
"max": 3.974376110434532,
"count": 120
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 509.2614874243736,
"min": 98.32729050517082,
"max": 935.9394870996475,
"count": 120
},
"Huggy.Policy.CuriosityReward.mean": {
"value": 0.8809918685505788,
"min": 0.0,
"max": 12.470365512838114,
"count": 120
},
"Huggy.Policy.CuriosityReward.sum": {
"value": 158.57853633910418,
"min": 0.0,
"max": 835.5144893601537,
"count": 120
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 120
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 120
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.012189299488672986,
"min": 0.011639445830951445,
"max": 0.026395128112344537,
"count": 73
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.012189299488672986,
"min": 0.011639445830951445,
"max": 0.026395128112344537,
"count": 73
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.010210927370935678,
"min": 0.010210927370935678,
"max": 0.030041808765381574,
"count": 73
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.010210927370935678,
"min": 0.010210927370935678,
"max": 0.030041808765381574,
"count": 73
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5809992840002503e-07,
"min": 3.5809992840002503e-07,
"max": 0.0004930911680484334,
"count": 73
},
"Huggy.Policy.LearningRate.sum": {
"value": 3.5809992840002503e-07,
"min": 3.5809992840002503e-07,
"max": 0.0004930911680484334,
"count": 73
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1001432,
"min": 0.1001432,
"max": 0.2972364666666667,
"count": 73
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.1001432,
"min": 0.1001432,
"max": 0.2972364666666667,
"count": 73
},
"Huggy.Policy.Beta.mean": {
"value": 1.7152840000000504e-05,
"min": 1.7152840000000504e-05,
"max": 0.009861961510000003,
"count": 73
},
"Huggy.Policy.Beta.sum": {
"value": 1.7152840000000504e-05,
"min": 1.7152840000000504e-05,
"max": 0.009861961510000003,
"count": 73
},
"Huggy.Losses.CuriosityForwardLoss.mean": {
"value": 0.3174527132511139,
"min": 0.24193540453910828,
"max": 3.4924210238456728,
"count": 73
},
"Huggy.Losses.CuriosityForwardLoss.sum": {
"value": 0.3174527132511139,
"min": 0.24193540453910828,
"max": 3.4924210238456728,
"count": 73
},
"Huggy.Losses.CuriosityInverseLoss.mean": {
"value": 4.899084987640381,
"min": 1.9119833207130432,
"max": 20.534766540527343,
"count": 73
},
"Huggy.Losses.CuriosityInverseLoss.sum": {
"value": 4.899084987640381,
"min": 1.9119833207130432,
"max": 20.534766540527343,
"count": 73
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1740844685",
"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": "1740849258"
},
"total": 4573.592033174,
"count": 1,
"self": 0.48836921400015854,
"children": {
"run_training.setup": {
"total": 0.023246384000003673,
"count": 1,
"self": 0.023246384000003673
},
"TrainerController.start_learning": {
"total": 4573.0804175759995,
"count": 1,
"self": 6.956126876941198,
"children": {
"TrainerController._reset_env": {
"total": 3.02688365899985,
"count": 1,
"self": 3.02688365899985
},
"TrainerController.advance": {
"total": 4562.587525670058,
"count": 345781,
"self": 7.073809786341371,
"children": {
"env_step": {
"total": 3128.1947832449005,
"count": 345781,
"self": 2425.258255383613,
"children": {
"SubprocessEnvManager._take_step": {
"total": 698.6232176699723,
"count": 345781,
"self": 24.231970147927314,
"children": {
"TorchPolicy.evaluate": {
"total": 674.391247522045,
"count": 334179,
"self": 674.391247522045
}
}
},
"workers": {
"total": 4.313310191315168,
"count": 345781,
"self": 0.0,
"children": {
"worker_root": {
"total": 4560.911430442862,
"count": 345781,
"is_parallel": true,
"self": 2579.514821446839,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009366310000586964,
"count": 1,
"is_parallel": true,
"self": 0.0002535880000777979,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006830429999808985,
"count": 2,
"is_parallel": true,
"self": 0.0006830429999808985
}
}
},
"UnityEnvironment.step": {
"total": 0.03182032499989873,
"count": 1,
"is_parallel": true,
"self": 0.00029097300011926563,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022053999987292627,
"count": 1,
"is_parallel": true,
"self": 0.00022053999987292627
},
"communicator.exchange": {
"total": 0.030396020999887696,
"count": 1,
"is_parallel": true,
"self": 0.030396020999887696
},
"steps_from_proto": {
"total": 0.0009127910000188422,
"count": 1,
"is_parallel": true,
"self": 0.00038623700015705253,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005265539998617896,
"count": 2,
"is_parallel": true,
"self": 0.0005265539998617896
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1981.396608996023,
"count": 345780,
"is_parallel": true,
"self": 56.21932599579418,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 130.25593857106742,
"count": 345780,
"is_parallel": true,
"self": 130.25593857106742
},
"communicator.exchange": {
"total": 1659.4781650720786,
"count": 345780,
"is_parallel": true,
"self": 1659.4781650720786
},
"steps_from_proto": {
"total": 135.44317935708273,
"count": 345780,
"is_parallel": true,
"self": 50.6635989462477,
"children": {
"_process_rank_one_or_two_observation": {
"total": 84.77958041083502,
"count": 691560,
"is_parallel": true,
"self": 84.77958041083502
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1427.318932638817,
"count": 345781,
"self": 10.518670767841513,
"children": {
"process_trajectory": {
"total": 323.23087566297545,
"count": 345781,
"self": 307.8463973359753,
"children": {
"RLTrainer._checkpoint": {
"total": 15.384478327000124,
"count": 30,
"self": 15.384478327000124
}
}
},
"_update_policy": {
"total": 1093.569386208,
"count": 73,
"self": 834.8409525980028,
"children": {
"TorchPPOOptimizer.update": {
"total": 258.7284336099972,
"count": 3650,
"self": 258.7284336099972
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.970000635599717e-07,
"count": 1,
"self": 8.970000635599717e-07
},
"TrainerController._save_models": {
"total": 0.5098804729996118,
"count": 1,
"self": 0.017614530000173545,
"children": {
"RLTrainer._checkpoint": {
"total": 0.49226594299943827,
"count": 1,
"self": 0.49226594299943827
}
}
}
}
}
}
}