ppo-Huggy / run_logs /timers.json
hankokk's picture
Huggy
0747949
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4001059532165527,
"min": 1.4001059532165527,
"max": 1.4262357950210571,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70527.5390625,
"min": 68675.765625,
"max": 76400.1796875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 99.08893280632411,
"min": 80.43457189014539,
"max": 389.06976744186045,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50139.0,
"min": 48689.0,
"max": 50190.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999970.0,
"min": 49761.0,
"max": 1999970.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999970.0,
"min": 49761.0,
"max": 1999970.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3854458332061768,
"min": 0.19197088479995728,
"max": 2.463238477706909,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1207.03564453125,
"min": 24.57227325439453,
"max": 1464.040771484375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7335063850455605,
"min": 2.1494610751979053,
"max": 3.96800927070112,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1889.1542308330536,
"min": 275.1310176253319,
"max": 2256.5353658795357,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7335063850455605,
"min": 2.1494610751979053,
"max": 3.96800927070112,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1889.1542308330536,
"min": 275.1310176253319,
"max": 2256.5353658795357,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0178692581725247,
"min": 0.012549569325953296,
"max": 0.0196778228089291,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0536077745175741,
"min": 0.02509913865190659,
"max": 0.0536077745175741,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04623687586022748,
"min": 0.020055137916157643,
"max": 0.060836315900087354,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.13871062758068245,
"min": 0.04011027583231529,
"max": 0.1649018527319034,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.303398898899997e-06,
"min": 3.303398898899997e-06,
"max": 0.00029534662655112504,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.910196696699991e-06,
"min": 9.910196696699991e-06,
"max": 0.0008441967186010998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10110110000000001,
"min": 0.10110110000000001,
"max": 0.198448875,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30330330000000005,
"min": 0.20734994999999995,
"max": 0.5813989,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.494488999999997e-05,
"min": 6.494488999999997e-05,
"max": 0.0049225988625,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019483466999999994,
"min": 0.00019483466999999994,
"max": 0.014071805109999998,
"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": "1697169539",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1697172025"
},
"total": 2485.9463773549996,
"count": 1,
"self": 0.44601210499968147,
"children": {
"run_training.setup": {
"total": 0.04574749300002168,
"count": 1,
"self": 0.04574749300002168
},
"TrainerController.start_learning": {
"total": 2485.454617757,
"count": 1,
"self": 4.7831611429651275,
"children": {
"TrainerController._reset_env": {
"total": 6.8924063860000615,
"count": 1,
"self": 6.8924063860000615
},
"TrainerController.advance": {
"total": 2473.6651498990345,
"count": 232170,
"self": 5.032572640197486,
"children": {
"env_step": {
"total": 1963.2287433880215,
"count": 232170,
"self": 1617.6500349718974,
"children": {
"SubprocessEnvManager._take_step": {
"total": 342.4893787770869,
"count": 232170,
"self": 16.753472183102417,
"children": {
"TorchPolicy.evaluate": {
"total": 325.7359065939845,
"count": 222962,
"self": 325.7359065939845
}
}
},
"workers": {
"total": 3.089329639037146,
"count": 232170,
"self": 0.0,
"children": {
"worker_root": {
"total": 2477.422039566938,
"count": 232170,
"is_parallel": true,
"self": 1162.731902535976,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008005770000636403,
"count": 1,
"is_parallel": true,
"self": 0.00022923200003788224,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000571345000025758,
"count": 2,
"is_parallel": true,
"self": 0.000571345000025758
}
}
},
"UnityEnvironment.step": {
"total": 0.0378586599999835,
"count": 1,
"is_parallel": true,
"self": 0.00029664000010143354,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025949499990929326,
"count": 1,
"is_parallel": true,
"self": 0.00025949499990929326
},
"communicator.exchange": {
"total": 0.03660245499997927,
"count": 1,
"is_parallel": true,
"self": 0.03660245499997927
},
"steps_from_proto": {
"total": 0.0007000699999935023,
"count": 1,
"is_parallel": true,
"self": 0.00018061599996599398,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005194540000275083,
"count": 2,
"is_parallel": true,
"self": 0.0005194540000275083
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1314.6901370309622,
"count": 232169,
"is_parallel": true,
"self": 40.845764620064756,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.70819476591385,
"count": 232169,
"is_parallel": true,
"self": 87.70819476591385
},
"communicator.exchange": {
"total": 1094.2236173499473,
"count": 232169,
"is_parallel": true,
"self": 1094.2236173499473
},
"steps_from_proto": {
"total": 91.91256029503631,
"count": 232169,
"is_parallel": true,
"self": 34.63787413414718,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.27468616088913,
"count": 464338,
"is_parallel": true,
"self": 57.27468616088913
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 505.40383387081545,
"count": 232170,
"self": 6.814107061782465,
"children": {
"process_trajectory": {
"total": 157.445090528033,
"count": 232170,
"self": 156.2424791360338,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2026113919991985,
"count": 10,
"self": 1.2026113919991985
}
}
},
"_update_policy": {
"total": 341.144636281,
"count": 97,
"self": 278.37708719199327,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.76754908900671,
"count": 2910,
"self": 62.76754908900671
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0650001058820635e-06,
"count": 1,
"self": 1.0650001058820635e-06
},
"TrainerController._save_models": {
"total": 0.11389926400033801,
"count": 1,
"self": 0.001985884000077931,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11191338000026008,
"count": 1,
"self": 0.11191338000026008
}
}
}
}
}
}
}