ppo-Huggy / run_logs /timers.json
pmohan6's picture
Huggy
8af5f46 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4037545919418335,
"min": 1.4037545919418335,
"max": 1.4270789623260498,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71086.1328125,
"min": 68947.5078125,
"max": 77604.4921875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 74.95896656534954,
"min": 74.95896656534954,
"max": 432.08620689655174,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49323.0,
"min": 48788.0,
"max": 50136.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999972.0,
"min": 49964.0,
"max": 1999972.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999972.0,
"min": 49964.0,
"max": 1999972.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4381418228149414,
"min": 0.012974785640835762,
"max": 2.496732234954834,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1604.2972412109375,
"min": 1.4921003580093384,
"max": 1604.2972412109375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7755209809016312,
"min": 1.79040763663209,
"max": 3.9324739044567325,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2484.2928054332733,
"min": 205.89687821269035,
"max": 2484.2928054332733,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7755209809016312,
"min": 1.79040763663209,
"max": 3.9324739044567325,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2484.2928054332733,
"min": 205.89687821269035,
"max": 2484.2928054332733,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01583178500667499,
"min": 0.013687662097314993,
"max": 0.020179455607042956,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04749535502002497,
"min": 0.027375324194629985,
"max": 0.055400664485447726,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05750079328815142,
"min": 0.02294718325138092,
"max": 0.05862250063154433,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17250237986445427,
"min": 0.04589436650276184,
"max": 0.175867501894633,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5117988294333407e-06,
"min": 3.5117988294333407e-06,
"max": 0.000295295476568175,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0535396488300022e-05,
"min": 1.0535396488300022e-05,
"max": 0.0008438832187056,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117056666666667,
"min": 0.10117056666666667,
"max": 0.19843182500000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035117,
"min": 0.20746325,
"max": 0.5812944000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.841127666666678e-05,
"min": 6.841127666666678e-05,
"max": 0.0049217480675,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020523383000000035,
"min": 0.00020523383000000035,
"max": 0.014066590560000002,
"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": "1742769137",
"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 --force",
"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": "1742771666"
},
"total": 2529.140221443,
"count": 1,
"self": 0.4240985810001803,
"children": {
"run_training.setup": {
"total": 0.03226392700003089,
"count": 1,
"self": 0.03226392700003089
},
"TrainerController.start_learning": {
"total": 2528.683858935,
"count": 1,
"self": 4.7424470441651465,
"children": {
"TrainerController._reset_env": {
"total": 3.4376263379999727,
"count": 1,
"self": 3.4376263379999727
},
"TrainerController.advance": {
"total": 2520.3800016658356,
"count": 232725,
"self": 4.905332173803345,
"children": {
"env_step": {
"total": 2031.4608806290203,
"count": 232725,
"self": 1593.6744675180594,
"children": {
"SubprocessEnvManager._take_step": {
"total": 434.8640377030372,
"count": 232725,
"self": 16.06175444809105,
"children": {
"TorchPolicy.evaluate": {
"total": 418.80228325494613,
"count": 222917,
"self": 418.80228325494613
}
}
},
"workers": {
"total": 2.9223754079237096,
"count": 232725,
"self": 0.0,
"children": {
"worker_root": {
"total": 2520.859361959985,
"count": 232725,
"is_parallel": true,
"self": 1222.719151973893,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009903279999434744,
"count": 1,
"is_parallel": true,
"self": 0.0002583759996923618,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007319520002511126,
"count": 2,
"is_parallel": true,
"self": 0.0007319520002511126
}
}
},
"UnityEnvironment.step": {
"total": 0.03446827300012956,
"count": 1,
"is_parallel": true,
"self": 0.0002931579999767564,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020124799993936904,
"count": 1,
"is_parallel": true,
"self": 0.00020124799993936904
},
"communicator.exchange": {
"total": 0.033056113000156984,
"count": 1,
"is_parallel": true,
"self": 0.033056113000156984
},
"steps_from_proto": {
"total": 0.0009177540000564477,
"count": 1,
"is_parallel": true,
"self": 0.00022110000008979114,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006966539999666566,
"count": 2,
"is_parallel": true,
"self": 0.0006966539999666566
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1298.140209986092,
"count": 232724,
"is_parallel": true,
"self": 37.43092902938383,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.83707156686364,
"count": 232724,
"is_parallel": true,
"self": 83.83707156686364
},
"communicator.exchange": {
"total": 1087.3681348008936,
"count": 232724,
"is_parallel": true,
"self": 1087.3681348008936
},
"steps_from_proto": {
"total": 89.50407458895097,
"count": 232724,
"is_parallel": true,
"self": 33.29067251977631,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.21340206917466,
"count": 465448,
"is_parallel": true,
"self": 56.21340206917466
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 484.013788863012,
"count": 232725,
"self": 7.264878225913662,
"children": {
"process_trajectory": {
"total": 171.71485325709796,
"count": 232725,
"self": 170.39375505209728,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3210982050006805,
"count": 10,
"self": 1.3210982050006805
}
}
},
"_update_policy": {
"total": 305.0340573800004,
"count": 97,
"self": 240.27899332501033,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.75506405499004,
"count": 2910,
"self": 64.75506405499004
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.569994290359318e-07,
"count": 1,
"self": 9.569994290359318e-07
},
"TrainerController._save_models": {
"total": 0.12378292999983387,
"count": 1,
"self": 0.00221310100005212,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12156982899978175,
"count": 1,
"self": 0.12156982899978175
}
}
}
}
}
}
}