ppo-Huggy / run_logs /timers.json
starrrlion's picture
Huggy
a5b02e0 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4039502143859863,
"min": 1.4039502143859863,
"max": 1.4264554977416992,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70938.796875,
"min": 69078.1171875,
"max": 76093.234375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 98.82834331337325,
"min": 83.08485856905158,
"max": 392.0390625,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49513.0,
"min": 48941.0,
"max": 50181.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999979.0,
"min": 49560.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999979.0,
"min": 49560.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.376554489135742,
"min": 0.06727733463048935,
"max": 2.4637556076049805,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1190.65380859375,
"min": 8.544221878051758,
"max": 1421.5390625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4930698582512174,
"min": 1.699024455284509,
"max": 3.8910422588580222,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1750.02799898386,
"min": 215.77610582113266,
"max": 2247.7937438488007,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4930698582512174,
"min": 1.699024455284509,
"max": 3.8910422588580222,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1750.02799898386,
"min": 215.77610582113266,
"max": 2247.7937438488007,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016313023382261035,
"min": 0.014355671762920488,
"max": 0.018968270798925206,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0489390701467831,
"min": 0.028711343525840975,
"max": 0.05690481239677562,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.051786774438288476,
"min": 0.022445250954478982,
"max": 0.05948567800223828,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15536032331486543,
"min": 0.044890501908957964,
"max": 0.17544806525111198,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5885488038500096e-06,
"min": 3.5885488038500096e-06,
"max": 0.00029537115154294996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0765646411550029e-05,
"min": 1.0765646411550029e-05,
"max": 0.00084433786855405,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10119615000000003,
"min": 0.10119615000000003,
"max": 0.19845705000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30358845000000007,
"min": 0.20753759999999996,
"max": 0.5814459499999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.968788500000016e-05,
"min": 6.968788500000016e-05,
"max": 0.004923006794999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002090636550000005,
"min": 0.0002090636550000005,
"max": 0.014074152905000002,
"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": "1719536025",
"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": "1719538559"
},
"total": 2534.618371871,
"count": 1,
"self": 0.8978277579999485,
"children": {
"run_training.setup": {
"total": 0.05895253800008504,
"count": 1,
"self": 0.05895253800008504
},
"TrainerController.start_learning": {
"total": 2533.661591575,
"count": 1,
"self": 4.479377291928358,
"children": {
"TrainerController._reset_env": {
"total": 3.32704029599995,
"count": 1,
"self": 3.32704029599995
},
"TrainerController.advance": {
"total": 2525.6723829140715,
"count": 232486,
"self": 5.035791035274087,
"children": {
"env_step": {
"total": 2003.124706629836,
"count": 232486,
"self": 1657.2573039767785,
"children": {
"SubprocessEnvManager._take_step": {
"total": 342.835476700903,
"count": 232486,
"self": 17.436726963971523,
"children": {
"TorchPolicy.evaluate": {
"total": 325.39874973693145,
"count": 223070,
"self": 325.39874973693145
}
}
},
"workers": {
"total": 3.0319259521546655,
"count": 232486,
"self": 0.0,
"children": {
"worker_root": {
"total": 2526.1523020580385,
"count": 232486,
"is_parallel": true,
"self": 1193.882958206123,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009604629999557801,
"count": 1,
"is_parallel": true,
"self": 0.0002283899998474226,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007320730001083575,
"count": 2,
"is_parallel": true,
"self": 0.0007320730001083575
}
}
},
"UnityEnvironment.step": {
"total": 0.05831356399994547,
"count": 1,
"is_parallel": true,
"self": 0.00042185899997093657,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001960609999969165,
"count": 1,
"is_parallel": true,
"self": 0.0001960609999969165
},
"communicator.exchange": {
"total": 0.05691545899992434,
"count": 1,
"is_parallel": true,
"self": 0.05691545899992434
},
"steps_from_proto": {
"total": 0.0007801850000532795,
"count": 1,
"is_parallel": true,
"self": 0.00022191800007931306,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005582669999739664,
"count": 2,
"is_parallel": true,
"self": 0.0005582669999739664
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1332.2693438519154,
"count": 232485,
"is_parallel": true,
"self": 40.35756034689257,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.47444528995834,
"count": 232485,
"is_parallel": true,
"self": 86.47444528995834
},
"communicator.exchange": {
"total": 1110.0673234990313,
"count": 232485,
"is_parallel": true,
"self": 1110.0673234990313
},
"steps_from_proto": {
"total": 95.3700147160331,
"count": 232485,
"is_parallel": true,
"self": 36.0883556320573,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.281659083975796,
"count": 464970,
"is_parallel": true,
"self": 59.281659083975796
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 517.5118852489612,
"count": 232486,
"self": 6.675800402999471,
"children": {
"process_trajectory": {
"total": 165.26083877996427,
"count": 232486,
"self": 163.77022741896383,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4906113610004468,
"count": 10,
"self": 1.4906113610004468
}
}
},
"_update_policy": {
"total": 345.5752460659975,
"count": 97,
"self": 280.0935644159987,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.48168164999879,
"count": 2910,
"self": 65.48168164999879
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.7759998627298046e-06,
"count": 1,
"self": 1.7759998627298046e-06
},
"TrainerController._save_models": {
"total": 0.18278929699999935,
"count": 1,
"self": 0.002887643000121898,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17990165399987745,
"count": 1,
"self": 0.17990165399987745
}
}
}
}
}
}
}