ppo-Huggy / run_logs /timers.json
hieu10x's picture
Huggy
b59f804 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4025628566741943,
"min": 1.4025628566741943,
"max": 1.4287678003311157,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 67780.25,
"min": 67084.7421875,
"max": 77286.7578125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 136.98066298342542,
"min": 94.90751445086705,
"max": 389.06976744186045,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49587.0,
"min": 48903.0,
"max": 50195.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999932.0,
"min": 49638.0,
"max": 1999932.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999932.0,
"min": 49638.0,
"max": 1999932.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.201986312866211,
"min": 0.1611095368862152,
"max": 2.4013915061950684,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 797.1190795898438,
"min": 20.622020721435547,
"max": 1215.279541015625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.2605134922167216,
"min": 1.9029482500627637,
"max": 3.81730432669136,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1180.3058841824532,
"min": 243.57737600803375,
"max": 1916.7759221196175,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.2605134922167216,
"min": 1.9029482500627637,
"max": 3.81730432669136,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1180.3058841824532,
"min": 243.57737600803375,
"max": 1916.7759221196175,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017074666582630016,
"min": 0.014001934202497068,
"max": 0.02002639610824796,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03414933316526003,
"min": 0.028003868404994137,
"max": 0.05982559691959371,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.040715473766128225,
"min": 0.022784279038508735,
"max": 0.05836217161267995,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.08143094753225645,
"min": 0.04556855807701747,
"max": 0.1709351268907388,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.3875985375e-06,
"min": 4.3875985375e-06,
"max": 0.00029529817656727495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.775197075e-06,
"min": 8.775197075e-06,
"max": 0.0008439522186826,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10146250000000001,
"min": 0.10146250000000001,
"max": 0.19843272499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20292500000000002,
"min": 0.20292500000000002,
"max": 0.5813174000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.297875e-05,
"min": 8.297875e-05,
"max": 0.004921792977499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001659575,
"min": 0.0001659575,
"max": 0.01406773826,
"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": "1737023607",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/content/py_venv/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": "2.5.1+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1737026171"
},
"total": 2564.2050132699997,
"count": 1,
"self": 0.441122551999797,
"children": {
"run_training.setup": {
"total": 0.020640554000010525,
"count": 1,
"self": 0.020640554000010525
},
"TrainerController.start_learning": {
"total": 2563.7432501639996,
"count": 1,
"self": 4.739388052017603,
"children": {
"TrainerController._reset_env": {
"total": 2.5550022869999793,
"count": 1,
"self": 2.5550022869999793
},
"TrainerController.advance": {
"total": 2556.3336720469815,
"count": 230863,
"self": 4.880019853860631,
"children": {
"env_step": {
"total": 2017.7654791880418,
"count": 230863,
"self": 1572.8553073709463,
"children": {
"SubprocessEnvManager._take_step": {
"total": 441.9784129571008,
"count": 230863,
"self": 16.19060283103431,
"children": {
"TorchPolicy.evaluate": {
"total": 425.78781012606646,
"count": 222989,
"self": 425.78781012606646
}
}
},
"workers": {
"total": 2.9317588599947157,
"count": 230863,
"self": 0.0,
"children": {
"worker_root": {
"total": 2555.8704875500343,
"count": 230863,
"is_parallel": true,
"self": 1278.0629670750727,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008721799999875657,
"count": 1,
"is_parallel": true,
"self": 0.0002522649999718851,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006199150000156806,
"count": 2,
"is_parallel": true,
"self": 0.0006199150000156806
}
}
},
"UnityEnvironment.step": {
"total": 0.031580964999875505,
"count": 1,
"is_parallel": true,
"self": 0.00035947899959865026,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018506100013837568,
"count": 1,
"is_parallel": true,
"self": 0.00018506100013837568
},
"communicator.exchange": {
"total": 0.02997262100006992,
"count": 1,
"is_parallel": true,
"self": 0.02997262100006992
},
"steps_from_proto": {
"total": 0.0010638040000685578,
"count": 1,
"is_parallel": true,
"self": 0.0002452439998705813,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008185600001979765,
"count": 2,
"is_parallel": true,
"self": 0.0008185600001979765
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1277.8075204749616,
"count": 230862,
"is_parallel": true,
"self": 37.57742588281553,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.98711231507173,
"count": 230862,
"is_parallel": true,
"self": 85.98711231507173
},
"communicator.exchange": {
"total": 1063.0289474899885,
"count": 230862,
"is_parallel": true,
"self": 1063.0289474899885
},
"steps_from_proto": {
"total": 91.2140347870859,
"count": 230862,
"is_parallel": true,
"self": 34.2213684379974,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.992666349088495,
"count": 461724,
"is_parallel": true,
"self": 56.992666349088495
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 533.6881730050791,
"count": 230863,
"self": 7.1361249013307315,
"children": {
"process_trajectory": {
"total": 163.21239621675045,
"count": 230863,
"self": 161.78372178474933,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4286744320011167,
"count": 10,
"self": 1.4286744320011167
}
}
},
"_update_policy": {
"total": 363.3396518869979,
"count": 96,
"self": 293.69247329300333,
"children": {
"TorchPPOOptimizer.update": {
"total": 69.64717859399457,
"count": 2880,
"self": 69.64717859399457
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4560000636265613e-06,
"count": 1,
"self": 1.4560000636265613e-06
},
"TrainerController._save_models": {
"total": 0.11518632200022694,
"count": 1,
"self": 0.002022305000537017,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11316401699968992,
"count": 1,
"self": 0.11316401699968992
}
}
}
}
}
}
}