ppo-Huggy / run_logs /timers.json
airboyyy's picture
Huggy
b53e90d verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4049420356750488,
"min": 1.4049420356750488,
"max": 1.4286963939666748,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69768.015625,
"min": 68855.21875,
"max": 77851.9765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 76.37616099071208,
"min": 71.24819624819625,
"max": 381.0229007633588,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49339.0,
"min": 48779.0,
"max": 50169.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999984.0,
"min": 49684.0,
"max": 1999984.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999984.0,
"min": 49684.0,
"max": 1999984.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.43696665763855,
"min": 0.142679825425148,
"max": 2.5561294555664062,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1574.280517578125,
"min": 18.548377990722656,
"max": 1716.5689697265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8031387164865853,
"min": 1.9941871063067362,
"max": 4.112614199255208,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2456.827610850334,
"min": 259.2443238198757,
"max": 2668.883211195469,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8031387164865853,
"min": 1.9941871063067362,
"max": 4.112614199255208,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2456.827610850334,
"min": 259.2443238198757,
"max": 2668.883211195469,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016828404232445693,
"min": 0.012726462901143046,
"max": 0.020188158992884078,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05048521269733708,
"min": 0.025452925802286093,
"max": 0.058152833080506144,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06219138469960955,
"min": 0.02115595436965426,
"max": 0.06507590264081954,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18657415409882866,
"min": 0.04231190873930852,
"max": 0.19522770792245864,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7818987394000015e-06,
"min": 3.7818987394000015e-06,
"max": 0.00029529345156885,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1345696218200005e-05,
"min": 1.1345696218200005e-05,
"max": 0.0008439354186881999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10126060000000003,
"min": 0.10126060000000003,
"max": 0.19843115000000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037818000000001,
"min": 0.20765324999999998,
"max": 0.5813118,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.290394000000003e-05,
"min": 7.290394000000003e-05,
"max": 0.0049217143849999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021871182000000007,
"min": 0.00021871182000000007,
"max": 0.014067458819999998,
"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": "1739530101",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739532658"
},
"total": 2556.4178789889997,
"count": 1,
"self": 0.49841523699979007,
"children": {
"run_training.setup": {
"total": 0.031474701000092864,
"count": 1,
"self": 0.031474701000092864
},
"TrainerController.start_learning": {
"total": 2555.8879890509997,
"count": 1,
"self": 4.491660764866538,
"children": {
"TrainerController._reset_env": {
"total": 3.5702847500000416,
"count": 1,
"self": 3.5702847500000416
},
"TrainerController.advance": {
"total": 2547.7015909151332,
"count": 233257,
"self": 4.981926548093725,
"children": {
"env_step": {
"total": 2037.496400192946,
"count": 233257,
"self": 1596.5209591550154,
"children": {
"SubprocessEnvManager._take_step": {
"total": 438.15695865290525,
"count": 233257,
"self": 16.215021336814402,
"children": {
"TorchPolicy.evaluate": {
"total": 421.94193731609084,
"count": 222916,
"self": 421.94193731609084
}
}
},
"workers": {
"total": 2.8184823850255043,
"count": 233257,
"self": 0.0,
"children": {
"worker_root": {
"total": 2548.424876895166,
"count": 233257,
"is_parallel": true,
"self": 1244.4096799670247,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0013433650000251873,
"count": 1,
"is_parallel": true,
"self": 0.0003342960001191386,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010090689999060487,
"count": 2,
"is_parallel": true,
"self": 0.0010090689999060487
}
}
},
"UnityEnvironment.step": {
"total": 0.03182919999994738,
"count": 1,
"is_parallel": true,
"self": 0.0003349819999129977,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019915200005016231,
"count": 1,
"is_parallel": true,
"self": 0.00019915200005016231
},
"communicator.exchange": {
"total": 0.03055407599993032,
"count": 1,
"is_parallel": true,
"self": 0.03055407599993032
},
"steps_from_proto": {
"total": 0.0007409900000538983,
"count": 1,
"is_parallel": true,
"self": 0.00019659100007629604,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005443989999776022,
"count": 2,
"is_parallel": true,
"self": 0.0005443989999776022
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1304.0151969281414,
"count": 233256,
"is_parallel": true,
"self": 39.670986210960336,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.30169039999942,
"count": 233256,
"is_parallel": true,
"self": 84.30169039999942
},
"communicator.exchange": {
"total": 1088.5200534670907,
"count": 233256,
"is_parallel": true,
"self": 1088.5200534670907
},
"steps_from_proto": {
"total": 91.52246685009095,
"count": 233256,
"is_parallel": true,
"self": 32.59797651109159,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.92449033899936,
"count": 466512,
"is_parallel": true,
"self": 58.92449033899936
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 505.2232641740933,
"count": 233257,
"self": 6.716282019022174,
"children": {
"process_trajectory": {
"total": 176.87966482207173,
"count": 233257,
"self": 175.33182876707167,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5478360550000616,
"count": 10,
"self": 1.5478360550000616
}
}
},
"_update_policy": {
"total": 321.6273173329994,
"count": 97,
"self": 253.96899988900304,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.65831744399634,
"count": 2910,
"self": 67.65831744399634
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0379999366705306e-06,
"count": 1,
"self": 1.0379999366705306e-06
},
"TrainerController._save_models": {
"total": 0.1244515829998818,
"count": 1,
"self": 0.0019752149996747903,
"children": {
"RLTrainer._checkpoint": {
"total": 0.122476368000207,
"count": 1,
"self": 0.122476368000207
}
}
}
}
}
}
}