FabioSG's picture
First Push
5254e7a verified
raw
history blame contribute delete
No virus
18.4 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.995456337928772,
"min": 0.995456337928772,
"max": 2.8720996379852295,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9504.6171875,
"min": 9504.6171875,
"max": 29413.171875,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.418313026428223,
"min": 0.28780004382133484,
"max": 12.418313026428223,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2421.571044921875,
"min": 55.83320617675781,
"max": 2523.77685546875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06755512036804301,
"min": 0.06160948092937378,
"max": 0.07333819698346905,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27022048147217204,
"min": 0.24743234614531198,
"max": 0.36136295871669877,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.24844926909780968,
"min": 0.11973466084786125,
"max": 0.27368672075224854,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9937970763912387,
"min": 0.478938643391445,
"max": 1.3684336037612428,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 23.75,
"min": 3.25,
"max": 24.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1045.0,
"min": 143.0,
"max": 1358.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.75,
"min": 3.25,
"max": 24.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1045.0,
"min": 143.0,
"max": 1358.0,
"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
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1717508776",
"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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1717509269"
},
"total": 493.308536472,
"count": 1,
"self": 0.4358931939999593,
"children": {
"run_training.setup": {
"total": 0.06021619300003067,
"count": 1,
"self": 0.06021619300003067
},
"TrainerController.start_learning": {
"total": 492.812427085,
"count": 1,
"self": 0.6419793810030683,
"children": {
"TrainerController._reset_env": {
"total": 2.9873183869999593,
"count": 1,
"self": 2.9873183869999593
},
"TrainerController.advance": {
"total": 489.0790240449969,
"count": 18201,
"self": 0.30847677099905013,
"children": {
"env_step": {
"total": 488.77054727399786,
"count": 18201,
"self": 320.46187917900255,
"children": {
"SubprocessEnvManager._take_step": {
"total": 167.98776630499583,
"count": 18201,
"self": 1.6103357339858348,
"children": {
"TorchPolicy.evaluate": {
"total": 166.37743057101,
"count": 18201,
"self": 166.37743057101
}
}
},
"workers": {
"total": 0.32090178999948193,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 491.4150496249998,
"count": 18201,
"is_parallel": true,
"self": 247.49242337299626,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005613878999952249,
"count": 1,
"is_parallel": true,
"self": 0.00401744599992071,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015964330000315385,
"count": 10,
"is_parallel": true,
"self": 0.0015964330000315385
}
}
},
"UnityEnvironment.step": {
"total": 0.0861173380000082,
"count": 1,
"is_parallel": true,
"self": 0.0006429380000554374,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046166300001004856,
"count": 1,
"is_parallel": true,
"self": 0.00046166300001004856
},
"communicator.exchange": {
"total": 0.08263164799996048,
"count": 1,
"is_parallel": true,
"self": 0.08263164799996048
},
"steps_from_proto": {
"total": 0.0023810889999822393,
"count": 1,
"is_parallel": true,
"self": 0.00039568899995856555,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001985400000023674,
"count": 10,
"is_parallel": true,
"self": 0.001985400000023674
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 243.92262625200357,
"count": 18200,
"is_parallel": true,
"self": 11.108758961986325,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.8732460860065885,
"count": 18200,
"is_parallel": true,
"self": 5.8732460860065885
},
"communicator.exchange": {
"total": 189.89109939500764,
"count": 18200,
"is_parallel": true,
"self": 189.89109939500764
},
"steps_from_proto": {
"total": 37.04952180900301,
"count": 18200,
"is_parallel": true,
"self": 7.2239145359839085,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.825607273019102,
"count": 182000,
"is_parallel": true,
"self": 29.825607273019102
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011165700004767132,
"count": 1,
"self": 0.00011165700004767132,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 482.8797167209968,
"count": 712247,
"is_parallel": true,
"self": 15.864568079978994,
"children": {
"process_trajectory": {
"total": 268.7433167590179,
"count": 712247,
"is_parallel": true,
"self": 267.85013687601776,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8931798830001298,
"count": 4,
"is_parallel": true,
"self": 0.8931798830001298
}
}
},
"_update_policy": {
"total": 198.2718318819999,
"count": 90,
"is_parallel": true,
"self": 66.43760442999877,
"children": {
"TorchPPOOptimizer.update": {
"total": 131.83422745200113,
"count": 4584,
"is_parallel": true,
"self": 131.83422745200113
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10399361500003579,
"count": 1,
"self": 0.001031097000122827,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10296251799991296,
"count": 1,
"self": 0.10296251799991296
}
}
}
}
}
}
}