ppo-Huggy / run_logs /timers.json
Supermani's picture
Huggy
015b02b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.409082055091858,
"min": 1.409082055091858,
"max": 1.428078532218933,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70268.1015625,
"min": 69622.9296875,
"max": 77086.3046875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 68.33425797503467,
"min": 65.52659574468085,
"max": 388.29457364341084,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49269.0,
"min": 49192.0,
"max": 50090.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999951.0,
"min": 49940.0,
"max": 1999951.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999951.0,
"min": 49940.0,
"max": 1999951.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.443892478942871,
"min": 0.1259753704071045,
"max": 2.5394058227539062,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1762.0465087890625,
"min": 16.124847412109375,
"max": 1870.887939453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7691608304454944,
"min": 1.7743475392926484,
"max": 4.051672629162117,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2717.5649587512016,
"min": 227.116485029459,
"max": 2918.598834514618,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7691608304454944,
"min": 1.7743475392926484,
"max": 4.051672629162117,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2717.5649587512016,
"min": 227.116485029459,
"max": 2918.598834514618,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016926091476731624,
"min": 0.01400221403843413,
"max": 0.021069639505185478,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05077827443019487,
"min": 0.02800442807686826,
"max": 0.05459140520688379,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0571570712245173,
"min": 0.02232187008485198,
"max": 0.06596031567702691,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1714712136735519,
"min": 0.04464374016970396,
"max": 0.18425561202069124,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.774198741966669e-06,
"min": 3.774198741966669e-06,
"max": 0.00029528992657002493,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1322596225900007e-05,
"min": 1.1322596225900007e-05,
"max": 0.00084390136869955,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10125803333333334,
"min": 0.10125803333333334,
"max": 0.19842997499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30377410000000005,
"min": 0.20766655000000006,
"max": 0.5813004500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.277586333333339e-05,
"min": 7.277586333333339e-05,
"max": 0.0049216557525,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021832759000000018,
"min": 0.00021832759000000018,
"max": 0.014066892455000002,
"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": "1722432045",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1722435194"
},
"total": 3149.4036076310003,
"count": 1,
"self": 0.5460444970003664,
"children": {
"run_training.setup": {
"total": 0.07295241700001043,
"count": 1,
"self": 0.07295241700001043
},
"TrainerController.start_learning": {
"total": 3148.784610717,
"count": 1,
"self": 5.698900086978938,
"children": {
"TrainerController._reset_env": {
"total": 3.4691227999999796,
"count": 1,
"self": 3.4691227999999796
},
"TrainerController.advance": {
"total": 3139.455599880021,
"count": 233677,
"self": 6.159854679080581,
"children": {
"env_step": {
"total": 2484.873055912911,
"count": 233677,
"self": 2016.6366819769876,
"children": {
"SubprocessEnvManager._take_step": {
"total": 464.5059457259292,
"count": 233677,
"self": 22.190906097947504,
"children": {
"TorchPolicy.evaluate": {
"total": 442.3150396279817,
"count": 222911,
"self": 442.3150396279817
}
}
},
"workers": {
"total": 3.730428209994045,
"count": 233677,
"self": 0.0,
"children": {
"worker_root": {
"total": 3139.5171913849777,
"count": 233677,
"is_parallel": true,
"self": 1526.3235741669866,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0013728430000128355,
"count": 1,
"is_parallel": true,
"self": 0.0003983869999615308,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009744560000513047,
"count": 2,
"is_parallel": true,
"self": 0.0009744560000513047
}
}
},
"UnityEnvironment.step": {
"total": 0.0435261630000241,
"count": 1,
"is_parallel": true,
"self": 0.0006085550000420881,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003160740000112128,
"count": 1,
"is_parallel": true,
"self": 0.0003160740000112128
},
"communicator.exchange": {
"total": 0.041566697999996904,
"count": 1,
"is_parallel": true,
"self": 0.041566697999996904
},
"steps_from_proto": {
"total": 0.0010348359999738932,
"count": 1,
"is_parallel": true,
"self": 0.0003088729999376483,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007259630000362449,
"count": 2,
"is_parallel": true,
"self": 0.0007259630000362449
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1613.193617217991,
"count": 233676,
"is_parallel": true,
"self": 47.12038964795556,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 111.08697860695594,
"count": 233676,
"is_parallel": true,
"self": 111.08697860695594
},
"communicator.exchange": {
"total": 1339.5181088120557,
"count": 233676,
"is_parallel": true,
"self": 1339.5181088120557
},
"steps_from_proto": {
"total": 115.46814015102382,
"count": 233676,
"is_parallel": true,
"self": 44.782524582030305,
"children": {
"_process_rank_one_or_two_observation": {
"total": 70.68561556899351,
"count": 467352,
"is_parallel": true,
"self": 70.68561556899351
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 648.4226892880299,
"count": 233677,
"self": 8.868455436950399,
"children": {
"process_trajectory": {
"total": 236.01212025308138,
"count": 233677,
"self": 233.78977160208166,
"children": {
"RLTrainer._checkpoint": {
"total": 2.22234865099972,
"count": 10,
"self": 2.22234865099972
}
}
},
"_update_policy": {
"total": 403.5421135979981,
"count": 97,
"self": 326.20613075299946,
"children": {
"TorchPPOOptimizer.update": {
"total": 77.33598284499863,
"count": 2910,
"self": 77.33598284499863
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.505999989603879e-06,
"count": 1,
"self": 1.505999989603879e-06
},
"TrainerController._save_models": {
"total": 0.16098644399971818,
"count": 1,
"self": 0.004623670000000857,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15636277399971732,
"count": 1,
"self": 0.15636277399971732
}
}
}
}
}
}
}