ppo-Huggy / run_logs /timers.json
zorgluf's picture
Huggy
accb756
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4046522378921509,
"min": 1.4046522378921509,
"max": 1.4277215003967285,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70450.3359375,
"min": 67071.4140625,
"max": 80360.0390625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.96596434359806,
"min": 77.1246105919003,
"max": 377.17164179104475,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49339.0,
"min": 48687.0,
"max": 50541.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999923.0,
"min": 49990.0,
"max": 1999923.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999923.0,
"min": 49990.0,
"max": 1999923.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.44350528717041,
"min": 0.04233916476368904,
"max": 2.49525785446167,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1507.6427001953125,
"min": 5.63110876083374,
"max": 1560.894287109375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7590476487019076,
"min": 1.7843162991050492,
"max": 4.025785264526446,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2319.332399249077,
"min": 237.31406778097153,
"max": 2445.164394080639,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7590476487019076,
"min": 1.7843162991050492,
"max": 4.025785264526446,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2319.332399249077,
"min": 237.31406778097153,
"max": 2445.164394080639,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019365218307939358,
"min": 0.012061159252334619,
"max": 0.02059654660261003,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.058095654923818074,
"min": 0.024122318504669237,
"max": 0.058095654923818074,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.061753728778825866,
"min": 0.022779720804343623,
"max": 0.0689020600169897,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1852611863364776,
"min": 0.045559441608687246,
"max": 0.19616794648269814,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.873798708766669e-06,
"min": 3.873798708766669e-06,
"max": 0.0002953837515387499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1621396126300008e-05,
"min": 1.1621396126300008e-05,
"max": 0.0008443252685582502,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10129123333333334,
"min": 0.10129123333333334,
"max": 0.19846124999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3038737,
"min": 0.20778969999999997,
"max": 0.5814417500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.443254333333338e-05,
"min": 7.443254333333338e-05,
"max": 0.004923216375,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022329763000000015,
"min": 0.00022329763000000015,
"max": 0.014073943324999994,
"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": "1686234218",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1686236546"
},
"total": 2327.949652544,
"count": 1,
"self": 0.3919353470000715,
"children": {
"run_training.setup": {
"total": 0.041735401999972055,
"count": 1,
"self": 0.041735401999972055
},
"TrainerController.start_learning": {
"total": 2327.515981795,
"count": 1,
"self": 4.189317238992771,
"children": {
"TrainerController._reset_env": {
"total": 4.688823262000028,
"count": 1,
"self": 4.688823262000028
},
"TrainerController.advance": {
"total": 2318.5181941880073,
"count": 233118,
"self": 4.285096843072097,
"children": {
"env_step": {
"total": 1796.5771110180053,
"count": 233118,
"self": 1508.715971199089,
"children": {
"SubprocessEnvManager._take_step": {
"total": 285.07993356300983,
"count": 233118,
"self": 16.44386592595447,
"children": {
"TorchPolicy.evaluate": {
"total": 268.63606763705536,
"count": 222958,
"self": 268.63606763705536
}
}
},
"workers": {
"total": 2.781206255906568,
"count": 233118,
"self": 0.0,
"children": {
"worker_root": {
"total": 2320.0655127560544,
"count": 233118,
"is_parallel": true,
"self": 1088.462343809148,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001039944000012838,
"count": 1,
"is_parallel": true,
"self": 0.0003228600000966253,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007170839999162126,
"count": 2,
"is_parallel": true,
"self": 0.0007170839999162126
}
}
},
"UnityEnvironment.step": {
"total": 0.049663648999967336,
"count": 1,
"is_parallel": true,
"self": 0.0003459919998931582,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023267400001714122,
"count": 1,
"is_parallel": true,
"self": 0.00023267400001714122
},
"communicator.exchange": {
"total": 0.04544792800004416,
"count": 1,
"is_parallel": true,
"self": 0.04544792800004416
},
"steps_from_proto": {
"total": 0.0036370550000128787,
"count": 1,
"is_parallel": true,
"self": 0.0002167779999808772,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0034202770000320015,
"count": 2,
"is_parallel": true,
"self": 0.0034202770000320015
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1231.6031689469064,
"count": 233117,
"is_parallel": true,
"self": 37.76502180091302,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 74.93682430391868,
"count": 233117,
"is_parallel": true,
"self": 74.93682430391868
},
"communicator.exchange": {
"total": 1027.0466906120669,
"count": 233117,
"is_parallel": true,
"self": 1027.0466906120669
},
"steps_from_proto": {
"total": 91.85463223000784,
"count": 233117,
"is_parallel": true,
"self": 33.210813243098414,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.64381898690942,
"count": 466234,
"is_parallel": true,
"self": 58.64381898690942
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 517.6559863269298,
"count": 233118,
"self": 6.679326293809254,
"children": {
"process_trajectory": {
"total": 136.3452832081215,
"count": 233118,
"self": 134.92031546012186,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4249677479996308,
"count": 10,
"self": 1.4249677479996308
}
}
},
"_update_policy": {
"total": 374.63137682499905,
"count": 97,
"self": 314.8305819099926,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.80079491500646,
"count": 2910,
"self": 59.80079491500646
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1319998520775698e-06,
"count": 1,
"self": 1.1319998520775698e-06
},
"TrainerController._save_models": {
"total": 0.11964597399992272,
"count": 1,
"self": 0.002116890999786847,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11752908300013587,
"count": 1,
"self": 0.11752908300013587
}
}
}
}
}
}
}