yepengsun's picture
First Push
7983d12 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7314770817756653,
"min": 0.7314770817756653,
"max": 2.849303960800171,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6951.9580078125,
"min": 6951.9580078125,
"max": 29085.6953125,
"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": 12.72491455078125,
"min": 0.4847988784313202,
"max": 12.72491455078125,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2481.3583984375,
"min": 94.05097961425781,
"max": 2570.8173828125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0630139352480696,
"min": 0.0630139352480696,
"max": 0.07558431619203047,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2520557409922784,
"min": 0.2520557409922784,
"max": 0.3779215809601524,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19968890866228178,
"min": 0.14792062388961294,
"max": 0.2978050366336224,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7987556346491271,
"min": 0.5916824955584518,
"max": 1.489025183168112,
"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": 24.818181818181817,
"min": 3.8181818181818183,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1092.0,
"min": 168.0,
"max": 1368.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.818181818181817,
"min": 3.8181818181818183,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1092.0,
"min": 168.0,
"max": 1368.0,
"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": "1757641065",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1757641433"
},
"total": 368.09587538799997,
"count": 1,
"self": 0.32360053799993693,
"children": {
"run_training.setup": {
"total": 0.02366324300010092,
"count": 1,
"self": 0.02366324300010092
},
"TrainerController.start_learning": {
"total": 367.74861160699993,
"count": 1,
"self": 0.3160093450178465,
"children": {
"TrainerController._reset_env": {
"total": 1.9971605529999579,
"count": 1,
"self": 1.9971605529999579
},
"TrainerController.advance": {
"total": 365.35633069498226,
"count": 18192,
"self": 0.3167316639664932,
"children": {
"env_step": {
"total": 253.27636852898559,
"count": 18192,
"self": 189.9540701519495,
"children": {
"SubprocessEnvManager._take_step": {
"total": 63.126738364983794,
"count": 18192,
"self": 1.1245127289616903,
"children": {
"TorchPolicy.evaluate": {
"total": 62.002225636022104,
"count": 18192,
"self": 62.002225636022104
}
}
},
"workers": {
"total": 0.19556001205228313,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 366.9539314339677,
"count": 18192,
"is_parallel": true,
"self": 198.8107278479406,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022536139999829174,
"count": 1,
"is_parallel": true,
"self": 0.0007077559994286275,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00154585800055429,
"count": 10,
"is_parallel": true,
"self": 0.00154585800055429
}
}
},
"UnityEnvironment.step": {
"total": 0.02644908399997803,
"count": 1,
"is_parallel": true,
"self": 0.0003571170000213897,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00026982700001099147,
"count": 1,
"is_parallel": true,
"self": 0.00026982700001099147
},
"communicator.exchange": {
"total": 0.024635449000015797,
"count": 1,
"is_parallel": true,
"self": 0.024635449000015797
},
"steps_from_proto": {
"total": 0.0011866909999298514,
"count": 1,
"is_parallel": true,
"self": 0.00024409799925706466,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009425930006727867,
"count": 10,
"is_parallel": true,
"self": 0.0009425930006727867
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 168.14320358602708,
"count": 18191,
"is_parallel": true,
"self": 5.767209073068443,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.2009209660163833,
"count": 18191,
"is_parallel": true,
"self": 3.2009209660163833
},
"communicator.exchange": {
"total": 140.48760520395126,
"count": 18191,
"is_parallel": true,
"self": 140.48760520395126
},
"steps_from_proto": {
"total": 18.687468342990996,
"count": 18191,
"is_parallel": true,
"self": 3.498713712891913,
"children": {
"_process_rank_one_or_two_observation": {
"total": 15.188754630099083,
"count": 181910,
"is_parallel": true,
"self": 15.188754630099083
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 111.76323050203018,
"count": 18192,
"self": 0.3778926290506206,
"children": {
"process_trajectory": {
"total": 24.486243214978458,
"count": 18192,
"self": 24.13116972797843,
"children": {
"RLTrainer._checkpoint": {
"total": 0.35507348700002694,
"count": 4,
"self": 0.35507348700002694
}
}
},
"_update_policy": {
"total": 86.8990946580011,
"count": 90,
"self": 34.962219797992475,
"children": {
"TorchPPOOptimizer.update": {
"total": 51.93687486000863,
"count": 4587,
"self": 51.93687486000863
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1180000001331791e-06,
"count": 1,
"self": 1.1180000001331791e-06
},
"TrainerController._save_models": {
"total": 0.07910989599986351,
"count": 1,
"self": 0.0009246270001312951,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07818526899973222,
"count": 1,
"self": 0.07818526899973222
}
}
}
}
}
}
}