Stoub's picture
First Push
135e50e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8114938735961914,
"min": 0.8114938735961914,
"max": 2.86527156829834,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7765.99609375,
"min": 7765.99609375,
"max": 29406.283203125,
"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": 13.060006141662598,
"min": 0.3520335257053375,
"max": 13.060006141662598,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2546.701171875,
"min": 68.29450225830078,
"max": 2617.046875,
"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": 0.0631197772627096,
"min": 0.0631197772627096,
"max": 0.07526769706101713,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2524791090508384,
"min": 0.2524791090508384,
"max": 0.36299557215876554,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20258845849072232,
"min": 0.10424807443575679,
"max": 0.2857516108482492,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8103538339628893,
"min": 0.41699229774302715,
"max": 1.3594844475680705,
"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": 26.113636363636363,
"min": 2.977272727272727,
"max": 26.113636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1149.0,
"min": 131.0,
"max": 1393.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.113636363636363,
"min": 2.977272727272727,
"max": 26.113636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1149.0,
"min": 131.0,
"max": 1393.0,
"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": "1727347791",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1727348378"
},
"total": 586.561463036,
"count": 1,
"self": 0.5297923530000617,
"children": {
"run_training.setup": {
"total": 0.06529966099998319,
"count": 1,
"self": 0.06529966099998319
},
"TrainerController.start_learning": {
"total": 585.966371022,
"count": 1,
"self": 0.804050545003065,
"children": {
"TrainerController._reset_env": {
"total": 2.6481609829999684,
"count": 1,
"self": 2.6481609829999684
},
"TrainerController.advance": {
"total": 582.431830871997,
"count": 18202,
"self": 0.41238432400768943,
"children": {
"env_step": {
"total": 582.0194465479893,
"count": 18202,
"self": 450.50649700399117,
"children": {
"SubprocessEnvManager._take_step": {
"total": 131.10299228400095,
"count": 18202,
"self": 2.282516324002188,
"children": {
"TorchPolicy.evaluate": {
"total": 128.82047595999876,
"count": 18202,
"self": 128.82047595999876
}
}
},
"workers": {
"total": 0.40995725999721344,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 584.1353932580079,
"count": 18202,
"is_parallel": true,
"self": 272.0898996270041,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0027055809999865232,
"count": 1,
"is_parallel": true,
"self": 0.0008096999998770116,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018958810001095117,
"count": 10,
"is_parallel": true,
"self": 0.0018958810001095117
}
}
},
"UnityEnvironment.step": {
"total": 0.056023466999988614,
"count": 1,
"is_parallel": true,
"self": 0.0008577520000017103,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004334469999776047,
"count": 1,
"is_parallel": true,
"self": 0.0004334469999776047
},
"communicator.exchange": {
"total": 0.05229551799999399,
"count": 1,
"is_parallel": true,
"self": 0.05229551799999399
},
"steps_from_proto": {
"total": 0.0024367500000153086,
"count": 1,
"is_parallel": true,
"self": 0.00045839099999511745,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001978359000020191,
"count": 10,
"is_parallel": true,
"self": 0.001978359000020191
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 312.04549363100375,
"count": 18201,
"is_parallel": true,
"self": 14.631989181996175,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.459280561000639,
"count": 18201,
"is_parallel": true,
"self": 7.459280561000639
},
"communicator.exchange": {
"total": 246.5060139370035,
"count": 18201,
"is_parallel": true,
"self": 246.5060139370035
},
"steps_from_proto": {
"total": 43.448209951003435,
"count": 18201,
"is_parallel": true,
"self": 8.710643482019634,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.7375664689838,
"count": 182010,
"is_parallel": true,
"self": 34.7375664689838
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00045990000000983855,
"count": 1,
"self": 0.00045990000000983855,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 575.7967428929279,
"count": 754307,
"is_parallel": true,
"self": 16.845755527911592,
"children": {
"process_trajectory": {
"total": 310.3863658870161,
"count": 754307,
"is_parallel": true,
"self": 309.77743092801614,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6089349589999529,
"count": 4,
"is_parallel": true,
"self": 0.6089349589999529
}
}
},
"_update_policy": {
"total": 248.56462147800016,
"count": 90,
"is_parallel": true,
"self": 71.28131425300114,
"children": {
"TorchPPOOptimizer.update": {
"total": 177.28330722499902,
"count": 4584,
"is_parallel": true,
"self": 177.28330722499902
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08186872199996742,
"count": 1,
"self": 0.001243484000042372,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08062523799992505,
"count": 1,
"self": 0.08062523799992505
}
}
}
}
}
}
}