houhui's picture
First Push
bb86f59 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.781438946723938,
"min": 0.7798269391059875,
"max": 2.8697378635406494,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7426.7958984375,
"min": 7426.7958984375,
"max": 29294.283203125,
"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": 13.239909172058105,
"min": 0.3274555504322052,
"max": 13.239909172058105,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2581.7822265625,
"min": 63.52637481689453,
"max": 2673.72314453125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06993779873243743,
"min": 0.05859475053536395,
"max": 0.07411321378381484,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2797511949297497,
"min": 0.2573185798342,
"max": 0.37056606891907423,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18436083960912977,
"min": 0.11695814325688772,
"max": 0.2886618559851366,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7374433584365191,
"min": 0.4678325730275509,
"max": 1.4000178195682227,
"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": 26.477272727272727,
"min": 3.3863636363636362,
"max": 26.477272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1165.0,
"min": 149.0,
"max": 1439.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.477272727272727,
"min": 3.3863636363636362,
"max": 26.477272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1165.0,
"min": 149.0,
"max": 1439.0,
"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": "1753948610",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/root/miniconda3/envs/mlagents/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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1753949253"
},
"total": 642.5274256318808,
"count": 1,
"self": 0.477433655411005,
"children": {
"run_training.setup": {
"total": 0.022499930113554,
"count": 1,
"self": 0.022499930113554
},
"TrainerController.start_learning": {
"total": 642.0274920463562,
"count": 1,
"self": 0.5008769668638706,
"children": {
"TrainerController._reset_env": {
"total": 2.39898382127285,
"count": 1,
"self": 2.39898382127285
},
"TrainerController.advance": {
"total": 639.0584753267467,
"count": 18192,
"self": 0.41917135939002037,
"children": {
"env_step": {
"total": 500.24985298141837,
"count": 18192,
"self": 446.2629156000912,
"children": {
"SubprocessEnvManager._take_step": {
"total": 53.66901019960642,
"count": 18192,
"self": 1.4026302993297577,
"children": {
"TorchPolicy.evaluate": {
"total": 52.26637990027666,
"count": 18192,
"self": 52.26637990027666
}
}
},
"workers": {
"total": 0.31792718172073364,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 640.4685519896448,
"count": 18192,
"is_parallel": true,
"self": 234.8955113440752,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001996878534555435,
"count": 1,
"is_parallel": true,
"self": 0.0005618371069431305,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014350414276123047,
"count": 10,
"is_parallel": true,
"self": 0.0014350414276123047
}
}
},
"UnityEnvironment.step": {
"total": 0.033975668251514435,
"count": 1,
"is_parallel": true,
"self": 0.0006918832659721375,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0006190463900566101,
"count": 1,
"is_parallel": true,
"self": 0.0006190463900566101
},
"communicator.exchange": {
"total": 0.03065868839621544,
"count": 1,
"is_parallel": true,
"self": 0.03065868839621544
},
"steps_from_proto": {
"total": 0.0020060501992702484,
"count": 1,
"is_parallel": true,
"self": 0.0004633702337741852,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015426799654960632,
"count": 10,
"is_parallel": true,
"self": 0.0015426799654960632
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 405.57304064556956,
"count": 18191,
"is_parallel": true,
"self": 15.988095436245203,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.507332403212786,
"count": 18191,
"is_parallel": true,
"self": 8.507332403212786
},
"communicator.exchange": {
"total": 334.75536319613457,
"count": 18191,
"is_parallel": true,
"self": 334.75536319613457
},
"steps_from_proto": {
"total": 46.32224960997701,
"count": 18191,
"is_parallel": true,
"self": 10.029944207519293,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.292305402457714,
"count": 181910,
"is_parallel": true,
"self": 36.292305402457714
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 138.3894509859383,
"count": 18192,
"self": 0.6632301993668079,
"children": {
"process_trajectory": {
"total": 26.07619458809495,
"count": 18192,
"self": 25.759014189243317,
"children": {
"RLTrainer._checkpoint": {
"total": 0.31718039885163307,
"count": 4,
"self": 0.31718039885163307
}
}
},
"_update_policy": {
"total": 111.65002619847655,
"count": 90,
"self": 48.90387366339564,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.74615253508091,
"count": 4587,
"self": 62.74615253508091
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4118850231170654e-06,
"count": 1,
"self": 1.4118850231170654e-06
},
"TrainerController._save_models": {
"total": 0.0691545195877552,
"count": 1,
"self": 0.00127449631690979,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06788002327084541,
"count": 1,
"self": 0.06788002327084541
}
}
}
}
}
}
}