PPO-Huggy / run_logs /timers.json
0xC4LL3's picture
First commit of trained PPO model for Huggy
96f937f
raw
history blame contribute delete
No virus
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4015724658966064,
"min": 1.4015724658966064,
"max": 1.4262281656265259,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70920.96875,
"min": 67843.796875,
"max": 77932.5546875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.42345276872965,
"min": 74.79848484848485,
"max": 392.1328125,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49380.0,
"min": 48819.0,
"max": 50193.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999923.0,
"min": 49953.0,
"max": 1999923.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999923.0,
"min": 49953.0,
"max": 1999923.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.485650062561035,
"min": 0.0008891054894775152,
"max": 2.5178382396698,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1526.189208984375,
"min": 0.11291639506816864,
"max": 1613.1832275390625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8295608712329927,
"min": 1.88413582730481,
"max": 4.00995477538901,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2351.3503749370575,
"min": 239.28525006771088,
"max": 2626.13206666708,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8295608712329927,
"min": 1.88413582730481,
"max": 4.00995477538901,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2351.3503749370575,
"min": 239.28525006771088,
"max": 2626.13206666708,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016401454708344924,
"min": 0.012478923842960891,
"max": 0.021005999934520028,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04920436412503477,
"min": 0.024957847685921783,
"max": 0.05758786653556551,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05811052819093068,
"min": 0.024403401650488377,
"max": 0.060783634024361766,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17433158457279205,
"min": 0.04880680330097675,
"max": 0.17433158457279205,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7281987573000015e-06,
"min": 3.7281987573000015e-06,
"max": 0.00029535930154689995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1184596271900004e-05,
"min": 1.1184596271900004e-05,
"max": 0.0008437089187637,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10124269999999998,
"min": 0.10124269999999998,
"max": 0.19845309999999994,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30372809999999995,
"min": 0.20765860000000008,
"max": 0.5812363,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.201073000000003e-05,
"min": 7.201073000000003e-05,
"max": 0.004922809689999998,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002160321900000001,
"min": 0.0002160321900000001,
"max": 0.01406369137,
"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": "1696509893",
"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": "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": "1696512493"
},
"total": 2600.439212755,
"count": 1,
"self": 0.49355297300007805,
"children": {
"run_training.setup": {
"total": 0.07803020099993319,
"count": 1,
"self": 0.07803020099993319
},
"TrainerController.start_learning": {
"total": 2599.867629581,
"count": 1,
"self": 4.760954703059269,
"children": {
"TrainerController._reset_env": {
"total": 6.347319689999949,
"count": 1,
"self": 6.347319689999949
},
"TrainerController.advance": {
"total": 2588.637183851941,
"count": 233350,
"self": 4.872464141951241,
"children": {
"env_step": {
"total": 1989.6903291360559,
"count": 233350,
"self": 1687.7264129220978,
"children": {
"SubprocessEnvManager._take_step": {
"total": 298.86118859200064,
"count": 233350,
"self": 17.168130222085324,
"children": {
"TorchPolicy.evaluate": {
"total": 281.6930583699153,
"count": 223022,
"self": 281.6930583699153
}
}
},
"workers": {
"total": 3.102727621957456,
"count": 233350,
"self": 0.0,
"children": {
"worker_root": {
"total": 2592.0090330180337,
"count": 233350,
"is_parallel": true,
"self": 1209.0361919040447,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001440773000012996,
"count": 1,
"is_parallel": true,
"self": 0.0003507910000735137,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010899819999394822,
"count": 2,
"is_parallel": true,
"self": 0.0010899819999394822
}
}
},
"UnityEnvironment.step": {
"total": 0.031740000000013424,
"count": 1,
"is_parallel": true,
"self": 0.00039244600009169517,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024400899997090164,
"count": 1,
"is_parallel": true,
"self": 0.00024400899997090164
},
"communicator.exchange": {
"total": 0.030299486999979308,
"count": 1,
"is_parallel": true,
"self": 0.030299486999979308
},
"steps_from_proto": {
"total": 0.0008040579999715192,
"count": 1,
"is_parallel": true,
"self": 0.00023458099997242243,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005694769999990967,
"count": 2,
"is_parallel": true,
"self": 0.0005694769999990967
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1382.972841113989,
"count": 233349,
"is_parallel": true,
"self": 42.145548010056245,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.87943846600353,
"count": 233349,
"is_parallel": true,
"self": 85.87943846600353
},
"communicator.exchange": {
"total": 1151.9975136129883,
"count": 233349,
"is_parallel": true,
"self": 1151.9975136129883
},
"steps_from_proto": {
"total": 102.95034102494094,
"count": 233349,
"is_parallel": true,
"self": 36.74946134188269,
"children": {
"_process_rank_one_or_two_observation": {
"total": 66.20087968305825,
"count": 466698,
"is_parallel": true,
"self": 66.20087968305825
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 594.0743905739336,
"count": 233350,
"self": 7.06302698194304,
"children": {
"process_trajectory": {
"total": 152.6432363249886,
"count": 233350,
"self": 151.19657409098852,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4466622340000868,
"count": 10,
"self": 1.4466622340000868
}
}
},
"_update_policy": {
"total": 434.3681272670019,
"count": 97,
"self": 371.9063187380009,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.46180852900102,
"count": 2910,
"self": 62.46180852900102
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0650001058820635e-06,
"count": 1,
"self": 1.0650001058820635e-06
},
"TrainerController._save_models": {
"total": 0.12217027099995903,
"count": 1,
"self": 0.0021061449997432646,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12006412600021577,
"count": 1,
"self": 0.12006412600021577
}
}
}
}
}
}
}