ucheokechukwu's picture
First Push
33e07f1 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.772698163986206,
"min": 2.7602391242980957,
"max": 2.8903253078460693,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 4056.45751953125,
"min": 1858.160400390625,
"max": 4211.0634765625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 19992.0,
"min": 960.0,
"max": 19992.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 19992.0,
"min": 960.0,
"max": 19992.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 1.5159350633621216,
"min": -0.03378257900476456,
"max": 1.5159350633621216,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 39.414310455322266,
"min": -0.5405212640762329,
"max": 39.414310455322266,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 9
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 2189.0,
"min": 2189.0,
"max": 2189.0,
"count": 9
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06878940116468013,
"min": 0.05870271082134351,
"max": 0.07665590503636528,
"count": 9
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.06878940116468013,
"min": 0.05870271082134351,
"max": 0.07665590503636528,
"count": 9
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21908724600193547,
"min": 0.09463478566384782,
"max": 0.21908724600193547,
"count": 9
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.21908724600193547,
"min": 0.09463478566384782,
"max": 0.21908724600193547,
"count": 9
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 4.320098559999991e-06,
"min": 4.320098559999991e-06,
"max": 0.00026832001056,
"count": 9
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 4.320098559999991e-06,
"min": 4.320098559999991e-06,
"max": 0.00026832001056,
"count": 9
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10144,
"min": 0.10144,
"max": 0.18944000000000003,
"count": 9
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10144,
"min": 0.10144,
"max": 0.18944000000000003,
"count": 9
},
"SnowballTarget.Policy.Beta.mean": {
"value": 8.185599999999986e-05,
"min": 8.185599999999986e-05,
"max": 0.0044730559999999996,
"count": 9
},
"SnowballTarget.Policy.Beta.sum": {
"value": 8.185599999999986e-05,
"min": 8.185599999999986e-05,
"max": 0.0044730559999999996,
"count": 9
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 5.909090909090909,
"min": 2.8181818181818183,
"max": 6.0,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 65.0,
"min": 6.0,
"max": 65.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 5.909090909090909,
"min": 2.8181818181818183,
"max": 6.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 65.0,
"min": 6.0,
"max": 65.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1705422145",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1705422198"
},
"total": 53.467113531999985,
"count": 1,
"self": 0.4513981369998419,
"children": {
"run_training.setup": {
"total": 0.051593099999990955,
"count": 1,
"self": 0.051593099999990955
},
"TrainerController.start_learning": {
"total": 52.96412229500015,
"count": 1,
"self": 0.08970175999888852,
"children": {
"TrainerController._reset_env": {
"total": 3.124518655999964,
"count": 1,
"self": 3.124518655999964
},
"TrainerController.advance": {
"total": 49.65441788900148,
"count": 1871,
"self": 0.0313715850029439,
"children": {
"env_step": {
"total": 49.623046303998535,
"count": 1871,
"self": 32.25105502200154,
"children": {
"SubprocessEnvManager._take_step": {
"total": 17.34061744499445,
"count": 1871,
"self": 0.16311442499954865,
"children": {
"TorchPolicy.evaluate": {
"total": 17.1775030199949,
"count": 1871,
"self": 17.1775030199949
}
}
},
"workers": {
"total": 0.03137383700254759,
"count": 1871,
"self": 0.0,
"children": {
"worker_root": {
"total": 52.77999933300407,
"count": 1871,
"is_parallel": true,
"self": 28.034848491002776,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004871061000130794,
"count": 1,
"is_parallel": true,
"self": 0.003422582999974111,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014484780001566833,
"count": 10,
"is_parallel": true,
"self": 0.0014484780001566833
}
}
},
"UnityEnvironment.step": {
"total": 0.042655893000073775,
"count": 1,
"is_parallel": true,
"self": 0.0007643069998266583,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000457948000075703,
"count": 1,
"is_parallel": true,
"self": 0.000457948000075703
},
"communicator.exchange": {
"total": 0.0389424450002025,
"count": 1,
"is_parallel": true,
"self": 0.0389424450002025
},
"steps_from_proto": {
"total": 0.0024911929999689164,
"count": 1,
"is_parallel": true,
"self": 0.0006399039996267675,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001851289000342149,
"count": 10,
"is_parallel": true,
"self": 0.001851289000342149
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 24.745150842001294,
"count": 1870,
"is_parallel": true,
"self": 1.1835049789958703,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.5930874129971926,
"count": 1870,
"is_parallel": true,
"self": 0.5930874129971926
},
"communicator.exchange": {
"total": 19.239189728003566,
"count": 1870,
"is_parallel": true,
"self": 19.239189728003566
},
"steps_from_proto": {
"total": 3.729368722004665,
"count": 1870,
"is_parallel": true,
"self": 0.6870707390028201,
"children": {
"_process_rank_one_or_two_observation": {
"total": 3.042297983001845,
"count": 18700,
"is_parallel": true,
"self": 3.042297983001845
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0002904609998495289,
"count": 1,
"self": 0.0002904609998495289,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 49.0303203599874,
"count": 76371,
"is_parallel": true,
"self": 1.6589532119905925,
"children": {
"process_trajectory": {
"total": 27.579449855996472,
"count": 76371,
"is_parallel": true,
"self": 27.07154272099615,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5079071350003233,
"count": 4,
"is_parallel": true,
"self": 0.5079071350003233
}
}
},
"_update_policy": {
"total": 19.791917292000335,
"count": 9,
"is_parallel": true,
"self": 6.381230058002302,
"children": {
"TorchPPOOptimizer.update": {
"total": 13.410687233998033,
"count": 456,
"is_parallel": true,
"self": 13.410687233998033
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09519352899997102,
"count": 1,
"self": 0.0009808140000586718,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09421271499991235,
"count": 1,
"self": 0.09421271499991235
}
}
}
}
}
}
}