ppo-Huggy / run_logs /timers.json
MaroueneSaidi's picture
Huggy
1186bc8 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4070132970809937,
"min": 1.4070132970809937,
"max": 1.426335096359253,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72368.3203125,
"min": 69236.453125,
"max": 77828.265625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 99.82128514056225,
"min": 91.57116451016635,
"max": 403.21774193548384,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49711.0,
"min": 48815.0,
"max": 50138.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999634.0,
"min": 49749.0,
"max": 1999634.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999634.0,
"min": 49749.0,
"max": 1999634.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3579764366149902,
"min": 0.059830352663993835,
"max": 2.3999884128570557,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1174.272216796875,
"min": 7.359133243560791,
"max": 1250.02490234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.523031797394695,
"min": 1.7527910764139842,
"max": 3.963243850525594,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1754.4698351025581,
"min": 215.59330239892006,
"max": 1982.2734741568565,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.523031797394695,
"min": 1.7527910764139842,
"max": 3.963243850525594,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1754.4698351025581,
"min": 215.59330239892006,
"max": 1982.2734741568565,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016043004977917816,
"min": 0.0129112043165757,
"max": 0.019840920692270933,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04812901493375345,
"min": 0.0258224086331514,
"max": 0.05827144262002548,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04797667703694767,
"min": 0.02202869349469741,
"max": 0.060427181836631566,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14393003111084302,
"min": 0.04405738698939482,
"max": 0.1812815455098947,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.272848909083335e-06,
"min": 3.272848909083335e-06,
"max": 0.00029526135157955,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.818546727250005e-06,
"min": 9.818546727250005e-06,
"max": 0.0008438010187329999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10109091666666668,
"min": 0.10109091666666668,
"max": 0.19842045,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30327275000000004,
"min": 0.2073142,
"max": 0.581267,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.443674166666671e-05,
"min": 6.443674166666671e-05,
"max": 0.004921180454999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019331022500000014,
"min": 0.00019331022500000014,
"max": 0.014065223300000002,
"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": "1733062484",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1733064865"
},
"total": 2380.980302743,
"count": 1,
"self": 0.8016013039996324,
"children": {
"run_training.setup": {
"total": 0.05690105000002177,
"count": 1,
"self": 0.05690105000002177
},
"TrainerController.start_learning": {
"total": 2380.1218003890003,
"count": 1,
"self": 4.310766601016439,
"children": {
"TrainerController._reset_env": {
"total": 5.021352605000004,
"count": 1,
"self": 5.021352605000004
},
"TrainerController.advance": {
"total": 2370.6157484409837,
"count": 231252,
"self": 4.249603191020924,
"children": {
"env_step": {
"total": 1878.9435990880154,
"count": 231252,
"self": 1473.726991917065,
"children": {
"SubprocessEnvManager._take_step": {
"total": 402.5631047189938,
"count": 231252,
"self": 15.222739712064254,
"children": {
"TorchPolicy.evaluate": {
"total": 387.3403650069296,
"count": 223074,
"self": 387.3403650069296
}
}
},
"workers": {
"total": 2.653502451956456,
"count": 231252,
"self": 0.0,
"children": {
"worker_root": {
"total": 2372.835269991069,
"count": 231252,
"is_parallel": true,
"self": 1172.27750965996,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008297869999864815,
"count": 1,
"is_parallel": true,
"self": 0.00023051499994153346,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005992720000449481,
"count": 2,
"is_parallel": true,
"self": 0.0005992720000449481
}
}
},
"UnityEnvironment.step": {
"total": 0.04432848099997955,
"count": 1,
"is_parallel": true,
"self": 0.000359071999923799,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020423899997012995,
"count": 1,
"is_parallel": true,
"self": 0.00020423899997012995
},
"communicator.exchange": {
"total": 0.04304913500004659,
"count": 1,
"is_parallel": true,
"self": 0.04304913500004659
},
"steps_from_proto": {
"total": 0.0007160350000390281,
"count": 1,
"is_parallel": true,
"self": 0.00019090500001084365,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005251300000281844,
"count": 2,
"is_parallel": true,
"self": 0.0005251300000281844
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1200.5577603311087,
"count": 231251,
"is_parallel": true,
"self": 36.7041728510701,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.27058705206014,
"count": 231251,
"is_parallel": true,
"self": 80.27058705206014
},
"communicator.exchange": {
"total": 997.3626040519752,
"count": 231251,
"is_parallel": true,
"self": 997.3626040519752
},
"steps_from_proto": {
"total": 86.22039637600352,
"count": 231251,
"is_parallel": true,
"self": 30.475755854919612,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.74464052108391,
"count": 462502,
"is_parallel": true,
"self": 55.74464052108391
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 487.42254616194754,
"count": 231252,
"self": 6.249820882897211,
"children": {
"process_trajectory": {
"total": 152.1229229770493,
"count": 231252,
"self": 150.80869089904985,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3142320779994634,
"count": 10,
"self": 1.3142320779994634
}
}
},
"_update_policy": {
"total": 329.049802302001,
"count": 97,
"self": 263.59840485900736,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.45139744299365,
"count": 2910,
"self": 65.45139744299365
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4269999155658297e-06,
"count": 1,
"self": 1.4269999155658297e-06
},
"TrainerController._save_models": {
"total": 0.17393131500011805,
"count": 1,
"self": 0.003025595000508474,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17090571999960957,
"count": 1,
"self": 0.17090571999960957
}
}
}
}
}
}
}