sususuaa123's picture
First Push
3dd55aa verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9159091711044312,
"min": 0.8985362648963928,
"max": 2.850088119506836,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8704.80078125,
"min": 8618.759765625,
"max": 29093.69921875,
"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": 12.94070053100586,
"min": 0.40793177485466003,
"max": 12.999634742736816,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2523.4365234375,
"min": 79.13876342773438,
"max": 2657.271484375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06878049259288603,
"min": 0.06208983525281,
"max": 0.07884675494906511,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2751219703715441,
"min": 0.26290275328695617,
"max": 0.3620831756861127,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21182284336171897,
"min": 0.13086932771565285,
"max": 0.2690480733472927,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8472913734468759,
"min": 0.5234773108626114,
"max": 1.2974135969199385,
"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": 25.34090909090909,
"min": 3.909090909090909,
"max": 25.65909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1115.0,
"min": 172.0,
"max": 1410.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.34090909090909,
"min": 3.909090909090909,
"max": 25.65909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1115.0,
"min": 172.0,
"max": 1410.0,
"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": "1752316534",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1752316955"
},
"total": 420.8240099540001,
"count": 1,
"self": 0.4340906109999878,
"children": {
"run_training.setup": {
"total": 0.022811740000065583,
"count": 1,
"self": 0.022811740000065583
},
"TrainerController.start_learning": {
"total": 420.367107603,
"count": 1,
"self": 0.3508926460096973,
"children": {
"TrainerController._reset_env": {
"total": 3.1877536519999694,
"count": 1,
"self": 3.1877536519999694
},
"TrainerController.advance": {
"total": 416.7305564979905,
"count": 18192,
"self": 0.3723166429825824,
"children": {
"env_step": {
"total": 299.69835216300544,
"count": 18192,
"self": 230.5426306149992,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.9517886970009,
"count": 18192,
"self": 1.2494433970052796,
"children": {
"TorchPolicy.evaluate": {
"total": 67.70234529999561,
"count": 18192,
"self": 67.70234529999561
}
}
},
"workers": {
"total": 0.20393285100533376,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 419.0408542199938,
"count": 18192,
"is_parallel": true,
"self": 216.2265127890024,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005758438000043498,
"count": 1,
"is_parallel": true,
"self": 0.004026355000178228,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017320829998652698,
"count": 10,
"is_parallel": true,
"self": 0.0017320829998652698
}
}
},
"UnityEnvironment.step": {
"total": 0.03445639200003825,
"count": 1,
"is_parallel": true,
"self": 0.0005929609999384411,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003893320000543099,
"count": 1,
"is_parallel": true,
"self": 0.0003893320000543099
},
"communicator.exchange": {
"total": 0.031705794999993486,
"count": 1,
"is_parallel": true,
"self": 0.031705794999993486
},
"steps_from_proto": {
"total": 0.0017683040000520123,
"count": 1,
"is_parallel": true,
"self": 0.0003579250001166656,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014103789999353467,
"count": 10,
"is_parallel": true,
"self": 0.0014103789999353467
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 202.81434143099136,
"count": 18191,
"is_parallel": true,
"self": 9.862917357993524,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.375961942992831,
"count": 18191,
"is_parallel": true,
"self": 5.375961942992831
},
"communicator.exchange": {
"total": 155.65465044000723,
"count": 18191,
"is_parallel": true,
"self": 155.65465044000723
},
"steps_from_proto": {
"total": 31.920811689997777,
"count": 18191,
"is_parallel": true,
"self": 5.721911632000911,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.198900057996866,
"count": 181910,
"is_parallel": true,
"self": 26.198900057996866
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 116.65988769200248,
"count": 18192,
"self": 0.4367351690026453,
"children": {
"process_trajectory": {
"total": 25.93576194700006,
"count": 18192,
"self": 25.533512296000026,
"children": {
"RLTrainer._checkpoint": {
"total": 0.40224965100003374,
"count": 4,
"self": 0.40224965100003374
}
}
},
"_update_policy": {
"total": 90.28739057599978,
"count": 90,
"self": 36.802433522001024,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.484957053998755,
"count": 4587,
"self": 53.484957053998755
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.051999902301759e-06,
"count": 1,
"self": 1.051999902301759e-06
},
"TrainerController._save_models": {
"total": 0.09790375499994752,
"count": 1,
"self": 0.0010277769999902375,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09687597799995729,
"count": 1,
"self": 0.09687597799995729
}
}
}
}
}
}
}