ppo-Huggy / run_logs /timers.json
Bhavesh7895's picture
Huggy
4be62a5 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4067785739898682,
"min": 1.4067785739898682,
"max": 1.4289863109588623,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71531.875,
"min": 68314.3359375,
"max": 78222.265625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 83.99659863945578,
"min": 72.12865497076024,
"max": 402.744,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49390.0,
"min": 48743.0,
"max": 50343.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999959.0,
"min": 49802.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999959.0,
"min": 49802.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.532788038253784,
"min": 0.003495474113151431,
"max": 2.545363664627075,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1489.279296875,
"min": 0.433438777923584,
"max": 1690.25244140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8538409022449636,
"min": 1.8181692173163737,
"max": 4.059155693830866,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2266.0584505200386,
"min": 225.45298294723034,
"max": 2679.0427579283714,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8538409022449636,
"min": 1.8181692173163737,
"max": 4.059155693830866,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2266.0584505200386,
"min": 225.45298294723034,
"max": 2679.0427579283714,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016480570675856954,
"min": 0.013089338998543098,
"max": 0.02111255502968561,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04944171202757086,
"min": 0.026178677997086196,
"max": 0.05710333310998976,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05955802065630753,
"min": 0.02348586721345782,
"max": 0.06929316651076078,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1786740619689226,
"min": 0.04697173442691564,
"max": 0.19113695907096068,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.731948756049991e-06,
"min": 3.731948756049991e-06,
"max": 0.000295311376562875,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1195846268149973e-05,
"min": 1.1195846268149973e-05,
"max": 0.0008439901686699499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10124394999999999,
"min": 0.10124394999999999,
"max": 0.198437125,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30373184999999997,
"min": 0.20762035,
"max": 0.58133005,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.207310499999988e-05,
"min": 7.207310499999988e-05,
"max": 0.004922012537499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021621931499999963,
"min": 0.00021621931499999963,
"max": 0.014068369495,
"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": "1740165175",
"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": "1740167689"
},
"total": 2513.680341187,
"count": 1,
"self": 0.6124356509994868,
"children": {
"run_training.setup": {
"total": 0.029713249999986147,
"count": 1,
"self": 0.029713249999986147
},
"TrainerController.start_learning": {
"total": 2513.0381922860006,
"count": 1,
"self": 4.645000933993742,
"children": {
"TrainerController._reset_env": {
"total": 2.948715174999961,
"count": 1,
"self": 2.948715174999961
},
"TrainerController.advance": {
"total": 2505.2680851190075,
"count": 233291,
"self": 5.00409676892059,
"children": {
"env_step": {
"total": 2011.9128485190013,
"count": 233291,
"self": 1577.8763596120466,
"children": {
"SubprocessEnvManager._take_step": {
"total": 431.21266556398655,
"count": 233291,
"self": 16.522889669064625,
"children": {
"TorchPolicy.evaluate": {
"total": 414.6897758949219,
"count": 222998,
"self": 414.6897758949219
}
}
},
"workers": {
"total": 2.823823342968126,
"count": 233291,
"self": 0.0,
"children": {
"worker_root": {
"total": 2505.11165848899,
"count": 233291,
"is_parallel": true,
"self": 1223.1647069298663,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001115561999995407,
"count": 1,
"is_parallel": true,
"self": 0.00024940700018305506,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008661549998123519,
"count": 2,
"is_parallel": true,
"self": 0.0008661549998123519
}
}
},
"UnityEnvironment.step": {
"total": 0.03328086900000926,
"count": 1,
"is_parallel": true,
"self": 0.00031455199973606796,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019031800002267119,
"count": 1,
"is_parallel": true,
"self": 0.00019031800002267119
},
"communicator.exchange": {
"total": 0.03205564200015942,
"count": 1,
"is_parallel": true,
"self": 0.03205564200015942
},
"steps_from_proto": {
"total": 0.0007203570000910986,
"count": 1,
"is_parallel": true,
"self": 0.00020893500004603993,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005114220000450587,
"count": 2,
"is_parallel": true,
"self": 0.0005114220000450587
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1281.9469515591238,
"count": 233290,
"is_parallel": true,
"self": 38.46004949542612,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.83761341087461,
"count": 233290,
"is_parallel": true,
"self": 82.83761341087461
},
"communicator.exchange": {
"total": 1070.0663375249242,
"count": 233290,
"is_parallel": true,
"self": 1070.0663375249242
},
"steps_from_proto": {
"total": 90.58295112789892,
"count": 233290,
"is_parallel": true,
"self": 33.37206694369388,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.21088418420504,
"count": 466580,
"is_parallel": true,
"self": 57.21088418420504
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 488.3511398310857,
"count": 233291,
"self": 6.881741605966681,
"children": {
"process_trajectory": {
"total": 175.64523517611724,
"count": 233291,
"self": 174.22043769111633,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4247974850009086,
"count": 10,
"self": 1.4247974850009086
}
}
},
"_update_policy": {
"total": 305.82416304900175,
"count": 97,
"self": 240.72346215500784,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.10070089399392,
"count": 2910,
"self": 65.10070089399392
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2459995559765957e-06,
"count": 1,
"self": 1.2459995559765957e-06
},
"TrainerController._save_models": {
"total": 0.17638981199979753,
"count": 1,
"self": 0.0023093820000212872,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17408042999977624,
"count": 1,
"self": 0.17408042999977624
}
}
}
}
}
}
}