ppo-Huggy / run_logs /timers.json
nardit's picture
Huggy
8aeac6f verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.398496150970459,
"min": 1.398496150970459,
"max": 1.4250754117965698,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71200.234375,
"min": 68200.4375,
"max": 77338.9453125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 102.23662551440329,
"min": 87.05105633802818,
"max": 417.8666666666667,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49687.0,
"min": 48773.0,
"max": 50199.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999512.0,
"min": 49909.0,
"max": 1999512.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999512.0,
"min": 49909.0,
"max": 1999512.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.392672300338745,
"min": 0.10914599150419235,
"max": 2.445929765701294,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1162.8387451171875,
"min": 12.988372802734375,
"max": 1325.919921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6610063340192958,
"min": 1.8051454004119425,
"max": 3.9335255238491764,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1779.2490783333778,
"min": 214.81230264902115,
"max": 2109.87198138237,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6610063340192958,
"min": 1.8051454004119425,
"max": 3.9335255238491764,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1779.2490783333778,
"min": 214.81230264902115,
"max": 2109.87198138237,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015115294615922419,
"min": 0.0139892381974884,
"max": 0.01929110828310109,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.030230589231844837,
"min": 0.0279784763949768,
"max": 0.05787332484930326,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.045290413933495685,
"min": 0.02165306912114223,
"max": 0.05833507776260376,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09058082786699137,
"min": 0.04330613824228446,
"max": 0.17337883040308955,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.686023438025011e-06,
"min": 4.686023438025011e-06,
"max": 0.000295356376547875,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.372046876050023e-06,
"min": 9.372046876050023e-06,
"max": 0.0008440356186547998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10156197499999997,
"min": 0.10156197499999997,
"max": 0.19845212500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20312394999999994,
"min": 0.20312394999999994,
"max": 0.5813452,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.794255250000022e-05,
"min": 8.794255250000022e-05,
"max": 0.004922761037500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017588510500000045,
"min": 0.00017588510500000045,
"max": 0.01406912548,
"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": "1751543015",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1751545477"
},
"total": 2462.572406176,
"count": 1,
"self": 0.5387853190004535,
"children": {
"run_training.setup": {
"total": 0.030425819999891246,
"count": 1,
"self": 0.030425819999891246
},
"TrainerController.start_learning": {
"total": 2462.003195037,
"count": 1,
"self": 4.222659743994882,
"children": {
"TrainerController._reset_env": {
"total": 3.029513372999986,
"count": 1,
"self": 3.029513372999986
},
"TrainerController.advance": {
"total": 2454.590763741005,
"count": 232160,
"self": 4.473652283183128,
"children": {
"env_step": {
"total": 1967.2912295479287,
"count": 232160,
"self": 1562.5194348629634,
"children": {
"SubprocessEnvManager._take_step": {
"total": 402.0035517469378,
"count": 232160,
"self": 15.129692622825473,
"children": {
"TorchPolicy.evaluate": {
"total": 386.8738591241123,
"count": 223092,
"self": 386.8738591241123
}
}
},
"workers": {
"total": 2.768242938027356,
"count": 232160,
"self": 0.0,
"children": {
"worker_root": {
"total": 2454.5757478180813,
"count": 232160,
"is_parallel": true,
"self": 1179.0555002430046,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008709059999318924,
"count": 1,
"is_parallel": true,
"self": 0.00025028299990026426,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006206230000316282,
"count": 2,
"is_parallel": true,
"self": 0.0006206230000316282
}
}
},
"UnityEnvironment.step": {
"total": 0.029583423999952174,
"count": 1,
"is_parallel": true,
"self": 0.0003213559999721838,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019625300001280266,
"count": 1,
"is_parallel": true,
"self": 0.00019625300001280266
},
"communicator.exchange": {
"total": 0.028352433000009114,
"count": 1,
"is_parallel": true,
"self": 0.028352433000009114
},
"steps_from_proto": {
"total": 0.0007133819999580737,
"count": 1,
"is_parallel": true,
"self": 0.0001958750000312648,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005175069999268089,
"count": 2,
"is_parallel": true,
"self": 0.0005175069999268089
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1275.5202475750766,
"count": 232159,
"is_parallel": true,
"self": 37.200208422078276,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.2864575809939,
"count": 232159,
"is_parallel": true,
"self": 82.2864575809939
},
"communicator.exchange": {
"total": 1068.1399984980592,
"count": 232159,
"is_parallel": true,
"self": 1068.1399984980592
},
"steps_from_proto": {
"total": 87.89358307394536,
"count": 232159,
"is_parallel": true,
"self": 32.81834533304436,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.075237740901,
"count": 464318,
"is_parallel": true,
"self": 55.075237740901
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 482.82588190989327,
"count": 232160,
"self": 6.5231710688865405,
"children": {
"process_trajectory": {
"total": 161.83063844500668,
"count": 232160,
"self": 160.45783772100617,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3728007240005127,
"count": 10,
"self": 1.3728007240005127
}
}
},
"_update_policy": {
"total": 314.47207239600004,
"count": 96,
"self": 253.8752228130038,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.59684958299624,
"count": 2880,
"self": 60.59684958299624
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2539999261207413e-06,
"count": 1,
"self": 1.2539999261207413e-06
},
"TrainerController._save_models": {
"total": 0.1602569249998851,
"count": 1,
"self": 0.0022524750002048677,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15800444999968022,
"count": 1,
"self": 0.15800444999968022
}
}
}
}
}
}
}