ChikeJ's picture
First Push SbT
1f6ba6d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8325057625770569,
"min": 0.8325057625770569,
"max": 2.8639371395111084,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8049.498046875,
"min": 8030.89306640625,
"max": 29361.083984375,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.490617752075195,
"min": 0.4159804582595825,
"max": 13.748686790466309,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2765.57666015625,
"min": 80.70021057128906,
"max": 2818.480712890625,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06474880396123683,
"min": 0.05975029402579107,
"max": 0.07756263376544595,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.32374401980618417,
"min": 0.2390011761031643,
"max": 0.3682731041723552,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1838021286854557,
"min": 0.13435424750159478,
"max": 0.2770784038539026,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9190106434272785,
"min": 0.5374169900063791,
"max": 1.385392019269513,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.0528989824000028e-06,
"min": 3.0528989824000028e-06,
"max": 0.00029675280108239997,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.5264494912000015e-05,
"min": 1.5264494912000015e-05,
"max": 0.001454064015312,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10101760000000001,
"min": 0.10101760000000001,
"max": 0.19891759999999997,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5050880000000001,
"min": 0.41199040000000003,
"max": 0.984688,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.0778240000000044e-05,
"min": 6.0778240000000044e-05,
"max": 0.00494598824,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0003038912000000002,
"min": 0.0003038912000000002,
"max": 0.0242359312,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.30909090909091,
"min": 4.0,
"max": 26.88888888888889,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1447.0,
"min": 176.0,
"max": 1475.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.30909090909091,
"min": 4.0,
"max": 26.88888888888889,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1447.0,
"min": 176.0,
"max": 1475.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1710589992",
"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/SnowballTarget3.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1710591195"
},
"total": 1203.7025551779998,
"count": 1,
"self": 0.4293405779999375,
"children": {
"run_training.setup": {
"total": 0.08885008300012487,
"count": 1,
"self": 0.08885008300012487
},
"TrainerController.start_learning": {
"total": 1203.1843645169997,
"count": 1,
"self": 1.6136236349880164,
"children": {
"TrainerController._reset_env": {
"total": 2.721673751000253,
"count": 1,
"self": 2.721673751000253
},
"TrainerController.advance": {
"total": 1198.7498570440116,
"count": 45476,
"self": 0.7392023790007443,
"children": {
"env_step": {
"total": 1198.0106546650109,
"count": 45476,
"self": 778.1463034910998,
"children": {
"SubprocessEnvManager._take_step": {
"total": 419.09742115998097,
"count": 45476,
"self": 3.941250968053282,
"children": {
"TorchPolicy.evaluate": {
"total": 415.1561701919277,
"count": 45476,
"self": 415.1561701919277
}
}
},
"workers": {
"total": 0.7669300139300503,
"count": 45476,
"self": 0.0,
"children": {
"worker_root": {
"total": 1200.0363319169473,
"count": 45476,
"is_parallel": true,
"self": 594.052956907899,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003188082000178838,
"count": 1,
"is_parallel": true,
"self": 0.0008713629999874684,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023167190001913696,
"count": 10,
"is_parallel": true,
"self": 0.0023167190001913696
}
}
},
"UnityEnvironment.step": {
"total": 0.042993497000225034,
"count": 1,
"is_parallel": true,
"self": 0.0008132500001920562,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004795009999725153,
"count": 1,
"is_parallel": true,
"self": 0.0004795009999725153
},
"communicator.exchange": {
"total": 0.039482283999859646,
"count": 1,
"is_parallel": true,
"self": 0.039482283999859646
},
"steps_from_proto": {
"total": 0.002218462000200816,
"count": 1,
"is_parallel": true,
"self": 0.00041629600082160323,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018021659993792127,
"count": 10,
"is_parallel": true,
"self": 0.0018021659993792127
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 605.9833750090484,
"count": 45475,
"is_parallel": true,
"self": 27.735946135953327,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 14.745634110012816,
"count": 45475,
"is_parallel": true,
"self": 14.745634110012816
},
"communicator.exchange": {
"total": 470.9336801370473,
"count": 45475,
"is_parallel": true,
"self": 470.9336801370473
},
"steps_from_proto": {
"total": 92.56811462603491,
"count": 45475,
"is_parallel": true,
"self": 17.650349722016017,
"children": {
"_process_rank_one_or_two_observation": {
"total": 74.9177649040189,
"count": 454750,
"is_parallel": true,
"self": 74.9177649040189
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013529999978345586,
"count": 1,
"self": 0.00013529999978345586,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1183.3259532064344,
"count": 1761967,
"is_parallel": true,
"self": 40.195186660128456,
"children": {
"process_trajectory": {
"total": 652.0610133253031,
"count": 1761967,
"is_parallel": true,
"self": 650.2733842163038,
"children": {
"RLTrainer._checkpoint": {
"total": 1.7876291089992264,
"count": 10,
"is_parallel": true,
"self": 1.7876291089992264
}
}
},
"_update_policy": {
"total": 491.0697532210029,
"count": 227,
"is_parallel": true,
"self": 141.42130564901436,
"children": {
"TorchPPOOptimizer.update": {
"total": 349.6484475719885,
"count": 11571,
"is_parallel": true,
"self": 349.6484475719885
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09907478700006322,
"count": 1,
"self": 0.001284220000343339,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09779056699971989,
"count": 1,
"self": 0.09779056699971989
}
}
}
}
}
}
}