siemr's picture
First Push
4b24791 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.270536184310913,
"min": 2.270536184310913,
"max": 2.270536184310913,
"count": 1
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 341495.46875,
"min": 341495.46875,
"max": 341495.46875,
"count": 1
},
"SnowballTarget.Step.mean": {
"value": 149984.0,
"min": 149984.0,
"max": 149984.0,
"count": 1
},
"SnowballTarget.Step.sum": {
"value": 149984.0,
"min": 149984.0,
"max": 149984.0,
"count": 1
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 4.399170398712158,
"min": 4.399170398712158,
"max": 4.399170398712158,
"count": 1
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 13188.712890625,
"min": 13188.712890625,
"max": 13188.712890625,
"count": 1
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 1
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 148852.0,
"min": 148852.0,
"max": 148852.0,
"count": 1
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 12.656417112299465,
"min": 12.656417112299465,
"max": 12.656417112299465,
"count": 1
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 9467.0,
"min": 9467.0,
"max": 9467.0,
"count": 1
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 12.656417112299465,
"min": 12.656417112299465,
"max": 12.656417112299465,
"count": 1
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 9467.0,
"min": 9467.0,
"max": 9467.0,
"count": 1
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.04727420671448815,
"min": 0.04727420671448815,
"max": 0.04727420671448815,
"count": 1
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 1.607323028292597,
"min": 1.607323028292597,
"max": 1.607323028292597,
"count": 1
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2467882486050594,
"min": 0.2467882486050594,
"max": 0.2467882486050594,
"count": 1
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 8.39080045257202,
"min": 8.39080045257202,
"max": 8.39080045257202,
"count": 1
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 0.00020770563076480002,
"min": 0.00020770563076480002,
"max": 0.00020770563076480002,
"count": 1
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.007061991446003201,
"min": 0.007061991446003201,
"max": 0.007061991446003201,
"count": 1
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1692352,
"min": 0.1692352,
"max": 0.1692352,
"count": 1
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 5.7539968,
"min": 5.7539968,
"max": 5.7539968,
"count": 1
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00346483648,
"min": 0.00346483648,
"max": 0.00346483648,
"count": 1
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.11780444032,
"min": 0.11780444032,
"max": 0.11780444032,
"count": 1
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1711919413",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711919854"
},
"total": 440.60167086900015,
"count": 1,
"self": 0.32140306800010876,
"children": {
"run_training.setup": {
"total": 0.05474280600014936,
"count": 1,
"self": 0.05474280600014936
},
"TrainerController.start_learning": {
"total": 440.2255249949999,
"count": 1,
"self": 0.5296336299711584,
"children": {
"TrainerController._reset_env": {
"total": 2.7210788539998703,
"count": 1,
"self": 2.7210788539998703
},
"TrainerController.advance": {
"total": 436.88679399202897,
"count": 22737,
"self": 0.2787891340472015,
"children": {
"env_step": {
"total": 436.60800485798177,
"count": 22737,
"self": 296.90586912396,
"children": {
"SubprocessEnvManager._take_step": {
"total": 139.4296536780239,
"count": 22737,
"self": 1.4931364100143583,
"children": {
"TorchPolicy.evaluate": {
"total": 137.93651726800954,
"count": 22737,
"self": 137.93651726800954
}
}
},
"workers": {
"total": 0.272482055997898,
"count": 22737,
"self": 0.0,
"children": {
"worker_root": {
"total": 439.4816661320142,
"count": 22737,
"is_parallel": true,
"self": 211.6958437400299,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002156782999918505,
"count": 1,
"is_parallel": true,
"self": 0.000609448999966844,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001547333999951661,
"count": 10,
"is_parallel": true,
"self": 0.001547333999951661
}
}
},
"UnityEnvironment.step": {
"total": 0.02875632400014183,
"count": 1,
"is_parallel": true,
"self": 0.0006906040000558278,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002805990000069869,
"count": 1,
"is_parallel": true,
"self": 0.0002805990000069869
},
"communicator.exchange": {
"total": 0.025744773000042187,
"count": 1,
"is_parallel": true,
"self": 0.025744773000042187
},
"steps_from_proto": {
"total": 0.002040348000036829,
"count": 1,
"is_parallel": true,
"self": 0.00039461499977733183,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016457330002594972,
"count": 10,
"is_parallel": true,
"self": 0.0016457330002594972
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 227.7858223919843,
"count": 22736,
"is_parallel": true,
"self": 8.526955388980241,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.5431358149830885,
"count": 22736,
"is_parallel": true,
"self": 4.5431358149830885
},
"communicator.exchange": {
"total": 186.90054185002873,
"count": 22736,
"is_parallel": true,
"self": 186.90054185002873
},
"steps_from_proto": {
"total": 27.81518933799225,
"count": 22736,
"is_parallel": true,
"self": 5.366210162962261,
"children": {
"_process_rank_one_or_two_observation": {
"total": 22.44897917502999,
"count": 227360,
"is_parallel": true,
"self": 22.44897917502999
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013148600010026712,
"count": 1,
"self": 0.00013148600010026712,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 435.29971036798815,
"count": 366179,
"is_parallel": true,
"self": 5.063797292042182,
"children": {
"process_trajectory": {
"total": 308.33275242794616,
"count": 366179,
"is_parallel": true,
"self": 307.8722772989461,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4604751290000877,
"count": 3,
"is_parallel": true,
"self": 0.4604751290000877
}
}
},
"_update_policy": {
"total": 121.90316064799981,
"count": 56,
"is_parallel": true,
"self": 44.24701296098988,
"children": {
"TorchPPOOptimizer.update": {
"total": 77.65614768700993,
"count": 2853,
"is_parallel": true,
"self": 77.65614768700993
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08788703299978806,
"count": 1,
"self": 0.0009298189997934969,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08695721399999456,
"count": 1,
"self": 0.08695721399999456
}
}
}
}
}
}
}