ppo-Huggy / run_logs /timers.json
ZZVic's picture
Huggy
c8131e4 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4094640016555786,
"min": 1.4094640016555786,
"max": 1.429405689239502,
"count": 37
},
"Huggy.Policy.Entropy.sum": {
"value": 70876.3046875,
"min": 823.1226806640625,
"max": 73851.671875,
"count": 37
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.63286713286713,
"min": 17.5,
"max": 187.65037593984962,
"count": 37
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48982.0,
"min": 35.0,
"max": 50162.0,
"count": 37
},
"Huggy.Step.mean": {
"value": 1999967.0,
"min": 199972.0,
"max": 1999967.0,
"count": 37
},
"Huggy.Step.sum": {
"value": 1999967.0,
"min": 199972.0,
"max": 1999967.0,
"count": 37
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.442965030670166,
"min": 0.6656661033630371,
"max": 2.465461254119873,
"count": 37
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1397.3759765625,
"min": 0.6656661033630371,
"max": 1459.95263671875,
"count": 37
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.797870560334279,
"min": 0.8976404666900635,
"max": 3.9586614463115946,
"count": 37
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2172.3819605112076,
"min": 0.8976404666900635,
"max": 2348.2892283797264,
"count": 37
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.797870560334279,
"min": 0.8976404666900635,
"max": 3.9586614463115946,
"count": 37
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2172.3819605112076,
"min": 0.8976404666900635,
"max": 2348.2892283797264,
"count": 37
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 37
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 37
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01541891013548593,
"min": 0.013350112098366177,
"max": 0.01878607398927367,
"count": 36
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03083782027097186,
"min": 0.026700224196732354,
"max": 0.054979618233240525,
"count": 36
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05185467079281807,
"min": 0.03156467859322826,
"max": 0.05885652924577395,
"count": 36
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10370934158563613,
"min": 0.06312935718645651,
"max": 0.17656958773732184,
"count": 36
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.0639239787249975e-06,
"min": 3.0639239787249975e-06,
"max": 0.00026532961155679996,
"count": 36
},
"Huggy.Policy.LearningRate.sum": {
"value": 6.127847957449995e-06,
"min": 6.127847957449995e-06,
"max": 0.0007541832486055999,
"count": 36
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10102127500000002,
"min": 0.10102127500000002,
"max": 0.18844320000000003,
"count": 36
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20204255000000004,
"min": 0.20204255000000004,
"max": 0.5513944,
"count": 36
},
"Huggy.Policy.Beta.mean": {
"value": 6.096162249999996e-05,
"min": 6.096162249999996e-05,
"max": 0.00442331568,
"count": 36
},
"Huggy.Policy.Beta.sum": {
"value": 0.00012192324499999992,
"min": 0.00012192324499999992,
"max": 0.012574580560000003,
"count": 36
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1764955591",
"python_version": "3.10.12 (main, Nov 4 2025, 08:48:33) [GCC 11.4.0]",
"command_line_arguments": "train_no_onnx.py ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy.x86_64 --run-id=Huggy --no-graphics --time-scale=20 --resume",
"mlagents_version": "1.1.0",
"mlagents_envs_version": "1.1.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.9.1+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1764959130"
},
"total": 3539.143241138,
"count": 1,
"self": 0.53533367,
"children": {
"run_training.setup": {
"total": 0.023884401000032085,
"count": 1,
"self": 0.023884401000032085
},
"TrainerController.start_learning": {
"total": 3538.584023067,
"count": 1,
"self": 6.148248026236615,
"children": {
"TrainerController._reset_env": {
"total": 1.97993346200019,
"count": 1,
"self": 1.97993346200019
},
"TrainerController.advance": {
"total": 3530.4022552717634,
"count": 209909,
"self": 6.060363806110217,
"children": {
"env_step": {
"total": 2269.201228407839,
"count": 209909,
"self": 1923.5588231043957,
"children": {
"SubprocessEnvManager._take_step": {
"total": 341.7130411882781,
"count": 209909,
"self": 20.043420552184216,
"children": {
"TorchPolicy.evaluate": {
"total": 321.6696206360939,
"count": 200732,
"self": 321.6696206360939
}
}
},
"workers": {
"total": 3.929364115165299,
"count": 209909,
"self": 0.0,
"children": {
"worker_root": {
"total": 3525.172949585779,
"count": 209909,
"is_parallel": true,
"self": 1978.7545093176022,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010102070000357344,
"count": 1,
"is_parallel": true,
"self": 0.0002539850011089584,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000756221998926776,
"count": 2,
"is_parallel": true,
"self": 0.000756221998926776
}
}
},
"UnityEnvironment.step": {
"total": 0.03935780700066971,
"count": 1,
"is_parallel": true,
"self": 0.00038404600036301417,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020377300006657606,
"count": 1,
"is_parallel": true,
"self": 0.00020377300006657606
},
"communicator.exchange": {
"total": 0.03602812700046343,
"count": 1,
"is_parallel": true,
"self": 0.03602812700046343
},
"steps_from_proto": {
"total": 0.0027418609997766907,
"count": 1,
"is_parallel": true,
"self": 0.0002325369996469817,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002509324000129709,
"count": 2,
"is_parallel": true,
"self": 0.002509324000129709
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1546.4184402681767,
"count": 209908,
"is_parallel": true,
"self": 44.41604829428343,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 93.38088755905937,
"count": 209908,
"is_parallel": true,
"self": 93.38088755905937
},
"communicator.exchange": {
"total": 1295.420343664142,
"count": 209908,
"is_parallel": true,
"self": 1295.420343664142
},
"steps_from_proto": {
"total": 113.201160750692,
"count": 209908,
"is_parallel": true,
"self": 37.61945833366826,
"children": {
"_process_rank_one_or_two_observation": {
"total": 75.58170241702373,
"count": 419816,
"is_parallel": true,
"self": 75.58170241702373
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1255.140663057814,
"count": 209909,
"self": 8.917875926598754,
"children": {
"process_trajectory": {
"total": 196.98567740621456,
"count": 209909,
"self": 196.45915426321244,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5265231430021231,
"count": 10,
"self": 0.5265231430021231
}
}
},
"_update_policy": {
"total": 1049.2371097250007,
"count": 87,
"self": 276.92138895596963,
"children": {
"TorchPPOOptimizer.update": {
"total": 772.315720769031,
"count": 2610,
"self": 772.315720769031
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0660005500540137e-06,
"count": 1,
"self": 1.0660005500540137e-06
},
"TrainerController._save_models": {
"total": 0.05358524099938222,
"count": 1,
"self": 0.00027638499886961654,
"children": {
"RLTrainer._checkpoint": {
"total": 0.053308856000512606,
"count": 1,
"self": 0.053308856000512606
}
}
}
}
}
}
}