tinywell's picture
step 200000
9773566 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9170640707015991,
"min": 0.9170640707015991,
"max": 2.860229730606079,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8756.1279296875,
"min": 8756.1279296875,
"max": 29260.150390625,
"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": 12.99020767211914,
"min": 0.326280802488327,
"max": 12.99020767211914,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2533.090576171875,
"min": 63.2984733581543,
"max": 2638.36376953125,
"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.Losses.PolicyLoss.mean": {
"value": 0.06786526505532617,
"min": 0.062182869404162316,
"max": 0.08021763855489839,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2714610602213047,
"min": 0.24873147761664927,
"max": 0.36555384002970054,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19483383474688903,
"min": 0.11548231221740043,
"max": 0.2769905658329234,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7793353389875561,
"min": 0.46192924886960174,
"max": 1.3849528291646171,
"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.CumulativeReward.mean": {
"value": 25.772727272727273,
"min": 3.4545454545454546,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1134.0,
"min": 152.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.772727272727273,
"min": 3.4545454545454546,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1134.0,
"min": 152.0,
"max": 1406.0,
"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": "1711017539",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=SnowballTarget2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711017971"
},
"total": 432.23780170099985,
"count": 1,
"self": 0.43628886299984515,
"children": {
"run_training.setup": {
"total": 0.05209177799997633,
"count": 1,
"self": 0.05209177799997633
},
"TrainerController.start_learning": {
"total": 431.74942106000003,
"count": 1,
"self": 0.5362670520089523,
"children": {
"TrainerController._reset_env": {
"total": 1.960719116999826,
"count": 1,
"self": 1.960719116999826
},
"TrainerController.advance": {
"total": 429.1619950759912,
"count": 18198,
"self": 0.26251593598635736,
"children": {
"env_step": {
"total": 428.8994791400048,
"count": 18198,
"self": 274.3759014199686,
"children": {
"SubprocessEnvManager._take_step": {
"total": 154.24752886000965,
"count": 18198,
"self": 1.4117804469999555,
"children": {
"TorchPolicy.evaluate": {
"total": 152.8357484130097,
"count": 18198,
"self": 152.8357484130097
}
}
},
"workers": {
"total": 0.27604886002654894,
"count": 18198,
"self": 0.0,
"children": {
"worker_root": {
"total": 430.6149070170154,
"count": 18198,
"is_parallel": true,
"self": 215.42083069100227,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022657389999949373,
"count": 1,
"is_parallel": true,
"self": 0.0006678599997940182,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015978790002009191,
"count": 10,
"is_parallel": true,
"self": 0.0015978790002009191
}
}
},
"UnityEnvironment.step": {
"total": 0.03645421500004886,
"count": 1,
"is_parallel": true,
"self": 0.0006825499999649765,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004073019999850658,
"count": 1,
"is_parallel": true,
"self": 0.0004073019999850658
},
"communicator.exchange": {
"total": 0.033227948000103424,
"count": 1,
"is_parallel": true,
"self": 0.033227948000103424
},
"steps_from_proto": {
"total": 0.002136414999995395,
"count": 1,
"is_parallel": true,
"self": 0.00041298300061498594,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017234319993804093,
"count": 10,
"is_parallel": true,
"self": 0.0017234319993804093
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 215.19407632601315,
"count": 18197,
"is_parallel": true,
"self": 10.024022665011444,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.21538268302038,
"count": 18197,
"is_parallel": true,
"self": 5.21538268302038
},
"communicator.exchange": {
"total": 167.40767174697453,
"count": 18197,
"is_parallel": true,
"self": 167.40767174697453
},
"steps_from_proto": {
"total": 32.546999231006794,
"count": 18197,
"is_parallel": true,
"self": 6.064365135041953,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.48263409596484,
"count": 181970,
"is_parallel": true,
"self": 26.48263409596484
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012526899990916718,
"count": 1,
"self": 0.00012526899990916718,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 423.68849228009753,
"count": 659375,
"is_parallel": true,
"self": 14.235416164080561,
"children": {
"process_trajectory": {
"total": 233.49233048901806,
"count": 659375,
"is_parallel": true,
"self": 232.82248147301766,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6698490160003985,
"count": 4,
"is_parallel": true,
"self": 0.6698490160003985
}
}
},
"_update_policy": {
"total": 175.96074562699891,
"count": 90,
"is_parallel": true,
"self": 50.79041540399794,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.17033022300097,
"count": 4587,
"is_parallel": true,
"self": 125.17033022300097
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09031454600017241,
"count": 1,
"self": 0.0010352740000598715,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08927927200011254,
"count": 1,
"self": 0.08927927200011254
}
}
}
}
}
}
}