ylzHug's picture
First Push
fd7a21c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9670000076293945,
"min": 0.9338895678520203,
"max": 2.828878879547119,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9190.3681640625,
"min": 9067.306640625,
"max": 28877.1953125,
"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": 12.32392406463623,
"min": 0.2728744447231293,
"max": 12.32392406463623,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2403.165283203125,
"min": 52.93764114379883,
"max": 2483.935302734375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07092864761958195,
"min": 0.06019869716906482,
"max": 0.07914166791855606,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2837145904783278,
"min": 0.24079478867625928,
"max": 0.3670479866531084,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17829866911850725,
"min": 0.11214814565655794,
"max": 0.3010033641521837,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.713194676474029,
"min": 0.44859258262623175,
"max": 1.4407012716812244,
"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": 24.204545454545453,
"min": 3.4545454545454546,
"max": 24.204545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1065.0,
"min": 152.0,
"max": 1325.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.204545454545453,
"min": 3.4545454545454546,
"max": 24.204545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1065.0,
"min": 152.0,
"max": 1325.0,
"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": "1758788530",
"python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1758788978"
},
"total": 447.77557785700014,
"count": 1,
"self": 0.8421006529997612,
"children": {
"run_training.setup": {
"total": 0.02437814800009619,
"count": 1,
"self": 0.02437814800009619
},
"TrainerController.start_learning": {
"total": 446.9090990560003,
"count": 1,
"self": 0.4106636200210687,
"children": {
"TrainerController._reset_env": {
"total": 2.818954286999997,
"count": 1,
"self": 2.818954286999997
},
"TrainerController.advance": {
"total": 443.5617756679792,
"count": 18192,
"self": 0.3993619489708635,
"children": {
"env_step": {
"total": 320.8216618119832,
"count": 18192,
"self": 250.242200902969,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.34212191602091,
"count": 18192,
"self": 1.3162844250180115,
"children": {
"TorchPolicy.evaluate": {
"total": 69.0258374910029,
"count": 18192,
"self": 69.0258374910029
}
}
},
"workers": {
"total": 0.23733899299327277,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 445.21855843093977,
"count": 18192,
"is_parallel": true,
"self": 225.4689668299893,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004800380999995468,
"count": 1,
"is_parallel": true,
"self": 0.003402927000024647,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013974539999708213,
"count": 10,
"is_parallel": true,
"self": 0.0013974539999708213
}
}
},
"UnityEnvironment.step": {
"total": 0.03757598900006087,
"count": 1,
"is_parallel": true,
"self": 0.0006446439999763243,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004236620000028779,
"count": 1,
"is_parallel": true,
"self": 0.0004236620000028779
},
"communicator.exchange": {
"total": 0.03449060000002646,
"count": 1,
"is_parallel": true,
"self": 0.03449060000002646
},
"steps_from_proto": {
"total": 0.0020170830000552087,
"count": 1,
"is_parallel": true,
"self": 0.0003988769999523356,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001618206000102873,
"count": 10,
"is_parallel": true,
"self": 0.001618206000102873
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 219.74959160095045,
"count": 18191,
"is_parallel": true,
"self": 10.388270334006165,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.6858124019604475,
"count": 18191,
"is_parallel": true,
"self": 5.6858124019604475
},
"communicator.exchange": {
"total": 166.6670817289944,
"count": 18191,
"is_parallel": true,
"self": 166.6670817289944
},
"steps_from_proto": {
"total": 37.00842713598945,
"count": 18191,
"is_parallel": true,
"self": 6.84996341998567,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.15846371600378,
"count": 181910,
"is_parallel": true,
"self": 30.15846371600378
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 122.34075190702515,
"count": 18192,
"self": 0.5142550700186348,
"children": {
"process_trajectory": {
"total": 26.971657345007543,
"count": 18192,
"self": 26.37316507300784,
"children": {
"RLTrainer._checkpoint": {
"total": 0.598492271999703,
"count": 4,
"self": 0.598492271999703
}
}
},
"_update_policy": {
"total": 94.85483949199897,
"count": 90,
"self": 40.04427617000033,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.81056332199864,
"count": 4587,
"self": 54.81056332199864
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3599997146229725e-06,
"count": 1,
"self": 1.3599997146229725e-06
},
"TrainerController._save_models": {
"total": 0.11770412100031535,
"count": 1,
"self": 0.0010328540001864894,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11667126700012886,
"count": 1,
"self": 0.11667126700012886
}
}
}
}
}
}
}