ppo-Huggy / run_logs /timers.json
SauravDevon's picture
Trained Huggy
0e60d22 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.404928207397461,
"min": 1.404928207397461,
"max": 1.4271659851074219,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70644.0078125,
"min": 69048.5625,
"max": 76729.90625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 86.79437609841828,
"min": 86.79437609841828,
"max": 414.26446280991735,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49386.0,
"min": 48738.0,
"max": 50144.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999922.0,
"min": 49651.0,
"max": 1999922.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999922.0,
"min": 49651.0,
"max": 1999922.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3983049392700195,
"min": 0.10346420109272003,
"max": 2.459277868270874,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1364.635498046875,
"min": 12.415703773498535,
"max": 1364.635498046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7355376977493138,
"min": 1.6562705755233764,
"max": 4.015884510072475,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2125.5209500193596,
"min": 198.75246906280518,
"max": 2194.6698775291443,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7355376977493138,
"min": 1.6562705755233764,
"max": 4.015884510072475,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2125.5209500193596,
"min": 198.75246906280518,
"max": 2194.6698775291443,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01645995157911481,
"min": 0.013191812614604715,
"max": 0.020431229192763564,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04937985473734442,
"min": 0.02638362522920943,
"max": 0.05674145501543535,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05825413378576438,
"min": 0.020797314355149865,
"max": 0.05913915541023016,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17476240135729312,
"min": 0.04159462871029973,
"max": 0.17476240135729312,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 2.258665537383336e-06,
"min": 2.258665537383336e-06,
"max": 0.0001969090015455,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 6.775996612150008e-06,
"min": 6.775996612150008e-06,
"max": 0.0005628670185665,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10112928333333333,
"min": 0.10112928333333333,
"max": 0.1984545,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30338785,
"min": 0.20739895000000003,
"max": 0.5814335,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.635123833333339e-05,
"min": 6.635123833333339e-05,
"max": 0.00492287955,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019905371500000019,
"min": 0.00019905371500000019,
"max": 0.014073531649999999,
"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": "1738306659",
"python_version": "3.10.12 (main, Jan 17 2025, 14:35:34) [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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1738309367"
},
"total": 2707.3777019649997,
"count": 1,
"self": 0.5437852949999069,
"children": {
"run_training.setup": {
"total": 0.023878569999851607,
"count": 1,
"self": 0.023878569999851607
},
"TrainerController.start_learning": {
"total": 2706.8100381,
"count": 1,
"self": 4.93360884909589,
"children": {
"TrainerController._reset_env": {
"total": 3.555700714000068,
"count": 1,
"self": 3.555700714000068
},
"TrainerController.advance": {
"total": 2698.2070706599047,
"count": 231969,
"self": 4.949076536779103,
"children": {
"env_step": {
"total": 2075.6661371559,
"count": 231969,
"self": 1620.2420949770535,
"children": {
"SubprocessEnvManager._take_step": {
"total": 452.3713646730157,
"count": 231969,
"self": 16.930349622032736,
"children": {
"TorchPolicy.evaluate": {
"total": 435.44101505098297,
"count": 222926,
"self": 435.44101505098297
}
}
},
"workers": {
"total": 3.0526775058306157,
"count": 231969,
"self": 0.0,
"children": {
"worker_root": {
"total": 2698.9140805587676,
"count": 231969,
"is_parallel": true,
"self": 1384.773745662868,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009457250002924411,
"count": 1,
"is_parallel": true,
"self": 0.0002747470007307129,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006709779995617282,
"count": 2,
"is_parallel": true,
"self": 0.0006709779995617282
}
}
},
"UnityEnvironment.step": {
"total": 0.04573753899967414,
"count": 1,
"is_parallel": true,
"self": 0.00029057100027785054,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020957099968654802,
"count": 1,
"is_parallel": true,
"self": 0.00020957099968654802
},
"communicator.exchange": {
"total": 0.04442781899979309,
"count": 1,
"is_parallel": true,
"self": 0.04442781899979309
},
"steps_from_proto": {
"total": 0.0008095779999166552,
"count": 1,
"is_parallel": true,
"self": 0.00018297799988431507,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006266000000323402,
"count": 2,
"is_parallel": true,
"self": 0.0006266000000323402
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1314.1403348958997,
"count": 231968,
"is_parallel": true,
"self": 37.90558328142606,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.21833651410407,
"count": 231968,
"is_parallel": true,
"self": 87.21833651410407
},
"communicator.exchange": {
"total": 1096.5520833990336,
"count": 231968,
"is_parallel": true,
"self": 1096.5520833990336
},
"steps_from_proto": {
"total": 92.46433170133605,
"count": 231968,
"is_parallel": true,
"self": 34.474331937338775,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.989999763997275,
"count": 463936,
"is_parallel": true,
"self": 57.989999763997275
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 617.5918569672258,
"count": 231969,
"self": 7.14628326607226,
"children": {
"process_trajectory": {
"total": 176.820930450152,
"count": 231969,
"self": 175.5406458001512,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2802846500007945,
"count": 10,
"self": 1.2802846500007945
}
}
},
"_update_policy": {
"total": 433.62464325100154,
"count": 97,
"self": 344.1745114949931,
"children": {
"TorchPPOOptimizer.update": {
"total": 89.45013175600843,
"count": 3880,
"self": 89.45013175600843
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.81999619398266e-07,
"count": 1,
"self": 9.81999619398266e-07
},
"TrainerController._save_models": {
"total": 0.11365689499962173,
"count": 1,
"self": 0.0019086359989159973,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11174825900070573,
"count": 1,
"self": 0.11174825900070573
}
}
}
}
}
}
}