ppo-Huggy / run_logs /timers.json
arhamk's picture
Huggy
2402740
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4100724458694458,
"min": 1.4100724458694458,
"max": 1.4309414625167847,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72051.8828125,
"min": 68640.1875,
"max": 75993.875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 116.64470588235294,
"min": 89.10144927536231,
"max": 399.528,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49574.0,
"min": 48866.0,
"max": 50148.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999984.0,
"min": 49318.0,
"max": 1999984.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999984.0,
"min": 49318.0,
"max": 1999984.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2711760997772217,
"min": 0.041279636323451996,
"max": 2.429579257965088,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 965.2498779296875,
"min": 5.1186747550964355,
"max": 1308.109619140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.333337487893946,
"min": 1.7454651623002944,
"max": 3.896254328020721,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1416.668432354927,
"min": 216.4376801252365,
"max": 2121.552093267441,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.333337487893946,
"min": 1.7454651623002944,
"max": 3.896254328020721,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1416.668432354927,
"min": 216.4376801252365,
"max": 2121.552093267441,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01707751780082213,
"min": 0.014022525313400064,
"max": 0.020934895841249575,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.051232553402466394,
"min": 0.028045050626800128,
"max": 0.056981387296885566,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.03951326898402638,
"min": 0.021933667610088983,
"max": 0.0562992492897643,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.11853980695207914,
"min": 0.043867335220177966,
"max": 0.1688977478692929,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4778488407500025e-06,
"min": 3.4778488407500025e-06,
"max": 0.00029535352654882493,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0433546522250007e-05,
"min": 1.0433546522250007e-05,
"max": 0.0008443353185548999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115924999999999,
"min": 0.10115924999999999,
"max": 0.19845117500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30347775,
"min": 0.20750185,
"max": 0.5814451000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.784657500000002e-05,
"min": 6.784657500000002e-05,
"max": 0.004922713632499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020353972500000006,
"min": 0.00020353972500000006,
"max": 0.01407411049,
"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": "1691002686",
"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": "1691005118"
},
"total": 2432.440207172,
"count": 1,
"self": 0.8129269760001989,
"children": {
"run_training.setup": {
"total": 0.04130038899995725,
"count": 1,
"self": 0.04130038899995725
},
"TrainerController.start_learning": {
"total": 2431.585979807,
"count": 1,
"self": 4.494231546037099,
"children": {
"TrainerController._reset_env": {
"total": 6.045290221999949,
"count": 1,
"self": 6.045290221999949
},
"TrainerController.advance": {
"total": 2420.855773519963,
"count": 231769,
"self": 4.620489177169475,
"children": {
"env_step": {
"total": 1871.69178288597,
"count": 231769,
"self": 1577.3146814041327,
"children": {
"SubprocessEnvManager._take_step": {
"total": 291.4595164309073,
"count": 231769,
"self": 17.146038831001874,
"children": {
"TorchPolicy.evaluate": {
"total": 274.3134775999054,
"count": 223060,
"self": 274.3134775999054
}
}
},
"workers": {
"total": 2.917585050930029,
"count": 231769,
"self": 0.0,
"children": {
"worker_root": {
"total": 2423.7713095540407,
"count": 231769,
"is_parallel": true,
"self": 1138.467359243093,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001044680999996217,
"count": 1,
"is_parallel": true,
"self": 0.00028793899997481276,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007567420000214042,
"count": 2,
"is_parallel": true,
"self": 0.0007567420000214042
}
}
},
"UnityEnvironment.step": {
"total": 0.03022121399999378,
"count": 1,
"is_parallel": true,
"self": 0.000333258999944519,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025177700001677294,
"count": 1,
"is_parallel": true,
"self": 0.00025177700001677294
},
"communicator.exchange": {
"total": 0.028935406000016428,
"count": 1,
"is_parallel": true,
"self": 0.028935406000016428
},
"steps_from_proto": {
"total": 0.0007007720000160589,
"count": 1,
"is_parallel": true,
"self": 0.0002094160000183365,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004913559999977224,
"count": 2,
"is_parallel": true,
"self": 0.0004913559999977224
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1285.3039503109478,
"count": 231768,
"is_parallel": true,
"self": 40.37734204085996,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.99467193801587,
"count": 231768,
"is_parallel": true,
"self": 80.99467193801587
},
"communicator.exchange": {
"total": 1065.3921925160073,
"count": 231768,
"is_parallel": true,
"self": 1065.3921925160073
},
"steps_from_proto": {
"total": 98.53974381606457,
"count": 231768,
"is_parallel": true,
"self": 34.78027430914807,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.7594695069165,
"count": 463536,
"is_parallel": true,
"self": 63.7594695069165
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 544.5435014568236,
"count": 231769,
"self": 7.046114175758021,
"children": {
"process_trajectory": {
"total": 133.87524294906524,
"count": 231769,
"self": 132.4922076460653,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3830353029999287,
"count": 10,
"self": 1.3830353029999287
}
}
},
"_update_policy": {
"total": 403.6221443320003,
"count": 97,
"self": 343.0467156199972,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.57542871200309,
"count": 2910,
"self": 60.57542871200309
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1580000318645034e-06,
"count": 1,
"self": 1.1580000318645034e-06
},
"TrainerController._save_models": {
"total": 0.1906833610000831,
"count": 1,
"self": 0.0026462570003786823,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1880371039997044,
"count": 1,
"self": 0.1880371039997044
}
}
}
}
}
}
}