ppo-Huggy / run_logs /timers.json
Creador270's picture
Huggy
d8f9fbe verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4015629291534424,
"min": 1.4015629291534424,
"max": 1.4293123483657837,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69251.2265625,
"min": 68802.890625,
"max": 76346.15625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 91.99257884972171,
"min": 84.30940170940171,
"max": 410.95081967213116,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49584.0,
"min": 48871.0,
"max": 50177.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999390.0,
"min": 49508.0,
"max": 1999390.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999390.0,
"min": 49508.0,
"max": 1999390.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3991951942443848,
"min": 0.05960061028599739,
"max": 2.429589033126831,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1293.166259765625,
"min": 7.211673736572266,
"max": 1412.0738525390625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7256296431863465,
"min": 1.7682789620781734,
"max": 3.8658090333853448,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2008.1143776774406,
"min": 213.96175441145897,
"max": 2245.814297914505,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7256296431863465,
"min": 1.7682789620781734,
"max": 3.8658090333853448,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2008.1143776774406,
"min": 213.96175441145897,
"max": 2245.814297914505,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01925894883202596,
"min": 0.01302943915919362,
"max": 0.020048133339150807,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05777684649607788,
"min": 0.02605887831838724,
"max": 0.05777684649607788,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.052187971067097445,
"min": 0.02420457289036777,
"max": 0.05800131460030874,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15656391320129234,
"min": 0.0501308628047506,
"max": 0.1740039438009262,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6674487775500027e-06,
"min": 3.6674487775500027e-06,
"max": 0.00029537827654057506,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1002346332650008e-05,
"min": 1.1002346332650008e-05,
"max": 0.0008444187185270999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10122245,
"min": 0.10122245,
"max": 0.19845942499999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30366735,
"min": 0.20757890000000004,
"max": 0.5814729,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.100025500000004e-05,
"min": 7.100025500000004e-05,
"max": 0.0049231253075,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021300076500000014,
"min": 0.00021300076500000014,
"max": 0.01407549771,
"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": "1720504663",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1720507133"
},
"total": 2469.774760487,
"count": 1,
"self": 0.4390229040000122,
"children": {
"run_training.setup": {
"total": 0.057141613999988294,
"count": 1,
"self": 0.057141613999988294
},
"TrainerController.start_learning": {
"total": 2469.278595969,
"count": 1,
"self": 4.737290512004165,
"children": {
"TrainerController._reset_env": {
"total": 3.1031292110000095,
"count": 1,
"self": 3.1031292110000095
},
"TrainerController.advance": {
"total": 2461.3176602499957,
"count": 232280,
"self": 5.164747575988713,
"children": {
"env_step": {
"total": 1950.6416910990658,
"count": 232280,
"self": 1610.3502269510627,
"children": {
"SubprocessEnvManager._take_step": {
"total": 337.2098439830206,
"count": 232280,
"self": 17.112138766106682,
"children": {
"TorchPolicy.evaluate": {
"total": 320.09770521691394,
"count": 222915,
"self": 320.09770521691394
}
}
},
"workers": {
"total": 3.0816201649824393,
"count": 232280,
"self": 0.0,
"children": {
"worker_root": {
"total": 2461.873486233922,
"count": 232280,
"is_parallel": true,
"self": 1167.7926291259773,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010145040000111294,
"count": 1,
"is_parallel": true,
"self": 0.0002454670000133774,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000769036999997752,
"count": 2,
"is_parallel": true,
"self": 0.000769036999997752
}
}
},
"UnityEnvironment.step": {
"total": 0.029938476999973318,
"count": 1,
"is_parallel": true,
"self": 0.00041320299999370036,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023095099999181912,
"count": 1,
"is_parallel": true,
"self": 0.00023095099999181912
},
"communicator.exchange": {
"total": 0.028512330000012298,
"count": 1,
"is_parallel": true,
"self": 0.028512330000012298
},
"steps_from_proto": {
"total": 0.0007819929999755004,
"count": 1,
"is_parallel": true,
"self": 0.00020501499994907135,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005769780000264291,
"count": 2,
"is_parallel": true,
"self": 0.0005769780000264291
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1294.0808571079447,
"count": 232279,
"is_parallel": true,
"self": 40.29954234596721,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.55047607204449,
"count": 232279,
"is_parallel": true,
"self": 80.55047607204449
},
"communicator.exchange": {
"total": 1080.641591359916,
"count": 232279,
"is_parallel": true,
"self": 1080.641591359916
},
"steps_from_proto": {
"total": 92.58924733001709,
"count": 232279,
"is_parallel": true,
"self": 32.85512687701231,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.73412045300478,
"count": 464558,
"is_parallel": true,
"self": 59.73412045300478
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 505.5112215749412,
"count": 232280,
"self": 7.078302119000739,
"children": {
"process_trajectory": {
"total": 157.01767781894006,
"count": 232280,
"self": 155.7355798089406,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2820980099994586,
"count": 10,
"self": 1.2820980099994586
}
}
},
"_update_policy": {
"total": 341.4152416370004,
"count": 97,
"self": 275.44989627098647,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.96534536601393,
"count": 2910,
"self": 65.96534536601393
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.420000424142927e-07,
"count": 1,
"self": 9.420000424142927e-07
},
"TrainerController._save_models": {
"total": 0.12051505399995222,
"count": 1,
"self": 0.0019818470000245725,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11853320699992764,
"count": 1,
"self": 0.11853320699992764
}
}
}
}
}
}
}