guife33's picture
First Push
2c3cea7 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9793391823768616,
"min": 0.9793391823768616,
"max": 2.8506979942321777,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9307.6396484375,
"min": 9307.6396484375,
"max": 29099.92578125,
"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": 12.778220176696777,
"min": 0.314750999212265,
"max": 12.778220176696777,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2491.7529296875,
"min": 61.06169128417969,
"max": 2587.69775390625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0705802435998111,
"min": 0.06462603672066597,
"max": 0.07459289177729492,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2823209743992444,
"min": 0.2585041468826639,
"max": 0.3729644588864746,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20582596490196153,
"min": 0.13343260712309868,
"max": 0.27832629999109343,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8233038596078461,
"min": 0.5337304284923947,
"max": 1.3594396850642037,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.522727272727273,
"min": 3.4318181818181817,
"max": 25.522727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1123.0,
"min": 151.0,
"max": 1366.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.522727272727273,
"min": 3.4318181818181817,
"max": 25.522727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1123.0,
"min": 151.0,
"max": 1366.0,
"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": "1741469569",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741469999"
},
"total": 430.19040823599994,
"count": 1,
"self": 0.43500181500007784,
"children": {
"run_training.setup": {
"total": 0.029803760999925544,
"count": 1,
"self": 0.029803760999925544
},
"TrainerController.start_learning": {
"total": 429.72560265999994,
"count": 1,
"self": 0.341246939997518,
"children": {
"TrainerController._reset_env": {
"total": 3.2168422329999657,
"count": 1,
"self": 3.2168422329999657
},
"TrainerController.advance": {
"total": 426.08218200200236,
"count": 18192,
"self": 0.36453386500124907,
"children": {
"env_step": {
"total": 302.79315805300314,
"count": 18192,
"self": 229.9356217069875,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.65239676200758,
"count": 18192,
"self": 1.2837042680059767,
"children": {
"TorchPolicy.evaluate": {
"total": 71.3686924940016,
"count": 18192,
"self": 71.3686924940016
}
}
},
"workers": {
"total": 0.20513958400806587,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 428.1901989240007,
"count": 18192,
"is_parallel": true,
"self": 226.37710559599805,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006321941000010156,
"count": 1,
"is_parallel": true,
"self": 0.003960115000040787,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002361825999969369,
"count": 10,
"is_parallel": true,
"self": 0.002361825999969369
}
}
},
"UnityEnvironment.step": {
"total": 0.03809183800001392,
"count": 1,
"is_parallel": true,
"self": 0.0006170299999439521,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044418400000267866,
"count": 1,
"is_parallel": true,
"self": 0.00044418400000267866
},
"communicator.exchange": {
"total": 0.03508476700005758,
"count": 1,
"is_parallel": true,
"self": 0.03508476700005758
},
"steps_from_proto": {
"total": 0.0019458570000097097,
"count": 1,
"is_parallel": true,
"self": 0.0003670320000992433,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015788249999104664,
"count": 10,
"is_parallel": true,
"self": 0.0015788249999104664
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 201.81309332800265,
"count": 18191,
"is_parallel": true,
"self": 9.790146954999159,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.392240812999717,
"count": 18191,
"is_parallel": true,
"self": 5.392240812999717
},
"communicator.exchange": {
"total": 154.4293663999989,
"count": 18191,
"is_parallel": true,
"self": 154.4293663999989
},
"steps_from_proto": {
"total": 32.20133916000486,
"count": 18191,
"is_parallel": true,
"self": 5.870147736991726,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.331191423013138,
"count": 181910,
"is_parallel": true,
"self": 26.331191423013138
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 122.92449008399797,
"count": 18192,
"self": 0.43395783499067875,
"children": {
"process_trajectory": {
"total": 27.08547856500752,
"count": 18192,
"self": 26.53689937500758,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5485791899999413,
"count": 4,
"self": 0.5485791899999413
}
}
},
"_update_policy": {
"total": 95.40505368399977,
"count": 90,
"self": 38.133515173003275,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.27153851099649,
"count": 4587,
"self": 57.27153851099649
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.06199991023459e-06,
"count": 1,
"self": 1.06199991023459e-06
},
"TrainerController._save_models": {
"total": 0.08533042300018678,
"count": 1,
"self": 0.0009030310002344777,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0844273919999523,
"count": 1,
"self": 0.0844273919999523
}
}
}
}
}
}
}