ppo-Huggy / run_logs /timers.json
SVBilenko's picture
Huggy
654b176 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4080663919448853,
"min": 1.4080663919448853,
"max": 1.4263964891433716,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71074.96875,
"min": 68271.0,
"max": 77499.484375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 70.74318507890962,
"min": 70.70114942528735,
"max": 389.69767441860466,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49308.0,
"min": 49208.0,
"max": 50271.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999971.0,
"min": 49954.0,
"max": 1999971.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999971.0,
"min": 49954.0,
"max": 1999971.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4633970260620117,
"min": -0.05872631072998047,
"max": 2.533935546875,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1716.98779296875,
"min": -7.5169677734375,
"max": 1725.1793212890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.824185806162217,
"min": 1.735996314266231,
"max": 4.099142329829732,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2665.4575068950653,
"min": 222.20752822607756,
"max": 2699.827569067478,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.824185806162217,
"min": 1.735996314266231,
"max": 4.099142329829732,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2665.4575068950653,
"min": 222.20752822607756,
"max": 2699.827569067478,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014118113293888098,
"min": 0.013473264726781052,
"max": 0.019892172347398526,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.042354339881664295,
"min": 0.0277129593778227,
"max": 0.05967651704219558,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06256572045385837,
"min": 0.02491889235874017,
"max": 0.06592079208542903,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1876971613615751,
"min": 0.04983778471748034,
"max": 0.19242613166570663,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.036148654650003e-06,
"min": 4.036148654650003e-06,
"max": 0.000295349926550025,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.2108445963950008e-05,
"min": 1.2108445963950008e-05,
"max": 0.0008442010685996501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10134535,
"min": 0.10134535,
"max": 0.198449975,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30403605,
"min": 0.20782759999999997,
"max": 0.58140035,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.713296500000003e-05,
"min": 7.713296500000003e-05,
"max": 0.004922653752500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002313988950000001,
"min": 0.0002313988950000001,
"max": 0.014071877465,
"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": "1756069013",
"python_version": "3.10.12 (main, May 27 2025, 17:12:29) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1756071437"
},
"total": 2424.302338761,
"count": 1,
"self": 0.48627490299986675,
"children": {
"run_training.setup": {
"total": 0.021699889000046824,
"count": 1,
"self": 0.021699889000046824
},
"TrainerController.start_learning": {
"total": 2423.794363969,
"count": 1,
"self": 4.175704124043023,
"children": {
"TrainerController._reset_env": {
"total": 2.9006077770000047,
"count": 1,
"self": 2.9006077770000047
},
"TrainerController.advance": {
"total": 2416.6139671519572,
"count": 233490,
"self": 4.387849387032929,
"children": {
"env_step": {
"total": 1937.2194940719662,
"count": 233490,
"self": 1536.7878034711352,
"children": {
"SubprocessEnvManager._take_step": {
"total": 397.6284413299185,
"count": 233490,
"self": 15.27171292488265,
"children": {
"TorchPolicy.evaluate": {
"total": 382.3567284050358,
"count": 222952,
"self": 382.3567284050358
}
}
},
"workers": {
"total": 2.803249270912602,
"count": 233490,
"self": 0.0,
"children": {
"worker_root": {
"total": 2416.523880192941,
"count": 233490,
"is_parallel": true,
"self": 1162.5066182519836,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008986420000383077,
"count": 1,
"is_parallel": true,
"self": 0.00026384699992831884,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006347950001099889,
"count": 2,
"is_parallel": true,
"self": 0.0006347950001099889
}
}
},
"UnityEnvironment.step": {
"total": 0.029006937000076505,
"count": 1,
"is_parallel": true,
"self": 0.00034075100006702996,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023380100003578264,
"count": 1,
"is_parallel": true,
"self": 0.00023380100003578264
},
"communicator.exchange": {
"total": 0.027740257999994355,
"count": 1,
"is_parallel": true,
"self": 0.027740257999994355
},
"steps_from_proto": {
"total": 0.0006921269999793367,
"count": 1,
"is_parallel": true,
"self": 0.00020396000002165238,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004881669999576843,
"count": 2,
"is_parallel": true,
"self": 0.0004881669999576843
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1254.0172619409573,
"count": 233489,
"is_parallel": true,
"self": 37.42633906276342,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.35432877108803,
"count": 233489,
"is_parallel": true,
"self": 82.35432877108803
},
"communicator.exchange": {
"total": 1044.012081328075,
"count": 233489,
"is_parallel": true,
"self": 1044.012081328075
},
"steps_from_proto": {
"total": 90.22451277903065,
"count": 233489,
"is_parallel": true,
"self": 33.55595679708995,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.6685559819407,
"count": 466978,
"is_parallel": true,
"self": 56.6685559819407
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 475.0066236929582,
"count": 233490,
"self": 6.355263779952111,
"children": {
"process_trajectory": {
"total": 161.56536533600536,
"count": 233490,
"self": 160.33542616800503,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2299391680003282,
"count": 10,
"self": 1.2299391680003282
}
}
},
"_update_policy": {
"total": 307.08599457700075,
"count": 97,
"self": 244.2312991899936,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.854695387007155,
"count": 2910,
"self": 62.854695387007155
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.289997251471505e-07,
"count": 1,
"self": 9.289997251471505e-07
},
"TrainerController._save_models": {
"total": 0.10408398700019461,
"count": 1,
"self": 0.0015085469999576162,
"children": {
"RLTrainer._checkpoint": {
"total": 0.102575440000237,
"count": 1,
"self": 0.102575440000237
}
}
}
}
}
}
}