rl_huggy / run_logs /timers.json
ShadeEngine's picture
Huggy RL agent
67b1933
raw
history blame
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4042587280273438,
"min": 1.4042587280273438,
"max": 1.4287781715393066,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70704.4296875,
"min": 69057.6875,
"max": 76400.375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 86.93157894736842,
"min": 73.62835820895522,
"max": 402.68548387096774,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49551.0,
"min": 49240.0,
"max": 49933.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999392.0,
"min": 49367.0,
"max": 1999392.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999392.0,
"min": 49367.0,
"max": 1999392.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.466883420944214,
"min": 0.16852883994579315,
"max": 2.5399129390716553,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1406.12353515625,
"min": 20.729047775268555,
"max": 1652.9080810546875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.694972164379923,
"min": 1.7915850179951365,
"max": 4.028047083882812,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2106.134133696556,
"min": 220.3649572134018,
"max": 2627.777039408684,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.694972164379923,
"min": 1.7915850179951365,
"max": 4.028047083882812,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2106.134133696556,
"min": 220.3649572134018,
"max": 2627.777039408684,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015837994926065826,
"min": 0.013429515545431057,
"max": 0.020794185611885042,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04751398477819748,
"min": 0.026859031090862115,
"max": 0.05802139069516367,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05187761402792401,
"min": 0.02109512311095993,
"max": 0.06396176554262638,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15563284208377204,
"min": 0.04219024622191986,
"max": 0.18757745251059532,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5911488029833286e-06,
"min": 3.5911488029833286e-06,
"max": 0.0002953455015515,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0773446408949985e-05,
"min": 1.0773446408949985e-05,
"max": 0.0008441217186261,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10119701666666665,
"min": 0.10119701666666665,
"max": 0.19844850000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30359105,
"min": 0.20752015000000001,
"max": 0.5813739,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.973113166666661e-05,
"min": 6.973113166666661e-05,
"max": 0.00492258015,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020919339499999982,
"min": 0.00020919339499999982,
"max": 0.01407055761,
"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": "1679743733",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1679746242"
},
"total": 2509.4079040640004,
"count": 1,
"self": 0.44092005199991036,
"children": {
"run_training.setup": {
"total": 0.11058568299995386,
"count": 1,
"self": 0.11058568299995386
},
"TrainerController.start_learning": {
"total": 2508.8563983290005,
"count": 1,
"self": 4.622867539941581,
"children": {
"TrainerController._reset_env": {
"total": 9.276922756999738,
"count": 1,
"self": 9.276922756999738
},
"TrainerController.advance": {
"total": 2494.8356991500596,
"count": 233361,
"self": 5.022829726976852,
"children": {
"env_step": {
"total": 1957.3346500669973,
"count": 233361,
"self": 1651.1669303291283,
"children": {
"SubprocessEnvManager._take_step": {
"total": 303.13901664312516,
"count": 233361,
"self": 18.23761782712245,
"children": {
"TorchPolicy.evaluate": {
"total": 284.9013988160027,
"count": 223061,
"self": 284.9013988160027
}
}
},
"workers": {
"total": 3.0287030947438325,
"count": 233361,
"self": 0.0,
"children": {
"worker_root": {
"total": 2500.1124664580666,
"count": 233361,
"is_parallel": true,
"self": 1159.7741135220608,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010619639997457853,
"count": 1,
"is_parallel": true,
"self": 0.00034406899931127555,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007178950004345097,
"count": 2,
"is_parallel": true,
"self": 0.0007178950004345097
}
}
},
"UnityEnvironment.step": {
"total": 0.04564484499996979,
"count": 1,
"is_parallel": true,
"self": 0.00035988000036013545,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022734999993190286,
"count": 1,
"is_parallel": true,
"self": 0.00022734999993190286
},
"communicator.exchange": {
"total": 0.04425426699981472,
"count": 1,
"is_parallel": true,
"self": 0.04425426699981472
},
"steps_from_proto": {
"total": 0.0008033479998630355,
"count": 1,
"is_parallel": true,
"self": 0.0002430080003250623,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005603399995379732,
"count": 2,
"is_parallel": true,
"self": 0.0005603399995379732
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1340.3383529360058,
"count": 233360,
"is_parallel": true,
"self": 39.097178950814396,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.74470320615819,
"count": 233360,
"is_parallel": true,
"self": 82.74470320615819
},
"communicator.exchange": {
"total": 1125.0510340289643,
"count": 233360,
"is_parallel": true,
"self": 1125.0510340289643
},
"steps_from_proto": {
"total": 93.4454367500689,
"count": 233360,
"is_parallel": true,
"self": 37.62209350220883,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.823343247860066,
"count": 466720,
"is_parallel": true,
"self": 55.823343247860066
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 532.4782193560854,
"count": 233361,
"self": 7.024521533181087,
"children": {
"process_trajectory": {
"total": 158.21057766090462,
"count": 233361,
"self": 156.75923889890373,
"children": {
"RLTrainer._checkpoint": {
"total": 1.451338762000887,
"count": 10,
"self": 1.451338762000887
}
}
},
"_update_policy": {
"total": 367.24312016199974,
"count": 97,
"self": 308.31571091900514,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.9274092429946,
"count": 2910,
"self": 58.9274092429946
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2699993021669798e-06,
"count": 1,
"self": 1.2699993021669798e-06
},
"TrainerController._save_models": {
"total": 0.1209076120003374,
"count": 1,
"self": 0.002001316000132647,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11890629600020475,
"count": 1,
"self": 0.11890629600020475
}
}
}
}
}
}
}