JDB03's picture
First commit
7de578c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9642803072929382,
"min": 0.9642803072929382,
"max": 2.859682083129883,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9185.734375,
"min": 9185.734375,
"max": 29348.91796875,
"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": 13.074403762817383,
"min": 0.2674157917499542,
"max": 13.074403762817383,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2549.5087890625,
"min": 51.878662109375,
"max": 2666.0517578125,
"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": 0.06670534119350087,
"min": 0.060698607322581886,
"max": 0.07506039612059134,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2668213647740035,
"min": 0.2541761918269627,
"max": 0.3753019806029567,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19395175024720968,
"min": 0.11061731908543437,
"max": 0.27884603700801436,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7758070009888387,
"min": 0.4424692763417375,
"max": 1.354613253298928,
"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": 25.40909090909091,
"min": 3.4318181818181817,
"max": 26.145454545454545,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1118.0,
"min": 151.0,
"max": 1438.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.40909090909091,
"min": 3.4318181818181817,
"max": 26.145454545454545,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1118.0,
"min": 151.0,
"max": 1438.0,
"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": "1705151556",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1705152017"
},
"total": 460.92447963100005,
"count": 1,
"self": 0.4247734070000888,
"children": {
"run_training.setup": {
"total": 0.046958194000012554,
"count": 1,
"self": 0.046958194000012554
},
"TrainerController.start_learning": {
"total": 460.45274802999995,
"count": 1,
"self": 0.6472370430138881,
"children": {
"TrainerController._reset_env": {
"total": 3.8371079009999676,
"count": 1,
"self": 3.8371079009999676
},
"TrainerController.advance": {
"total": 455.88002160598614,
"count": 18197,
"self": 0.33125149998454617,
"children": {
"env_step": {
"total": 455.5487701060016,
"count": 18197,
"self": 301.000249335995,
"children": {
"SubprocessEnvManager._take_step": {
"total": 154.220491185009,
"count": 18197,
"self": 1.5495469340023647,
"children": {
"TorchPolicy.evaluate": {
"total": 152.67094425100663,
"count": 18197,
"self": 152.67094425100663
}
}
},
"workers": {
"total": 0.32802958499758006,
"count": 18197,
"self": 0.0,
"children": {
"worker_root": {
"total": 459.099794755998,
"count": 18197,
"is_parallel": true,
"self": 225.04169804701235,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00579096700005266,
"count": 1,
"is_parallel": true,
"self": 0.003989822000107779,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018011449999448814,
"count": 10,
"is_parallel": true,
"self": 0.0018011449999448814
}
}
},
"UnityEnvironment.step": {
"total": 0.0374813460000496,
"count": 1,
"is_parallel": true,
"self": 0.0006256410000560209,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041357800000696443,
"count": 1,
"is_parallel": true,
"self": 0.00041357800000696443
},
"communicator.exchange": {
"total": 0.03452471399998558,
"count": 1,
"is_parallel": true,
"self": 0.03452471399998558
},
"steps_from_proto": {
"total": 0.0019174130000010337,
"count": 1,
"is_parallel": true,
"self": 0.0003998120000687777,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001517600999932256,
"count": 10,
"is_parallel": true,
"self": 0.001517600999932256
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 234.05809670898566,
"count": 18196,
"is_parallel": true,
"self": 10.806463783974664,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.572788382008753,
"count": 18196,
"is_parallel": true,
"self": 5.572788382008753
},
"communicator.exchange": {
"total": 184.01663363599687,
"count": 18196,
"is_parallel": true,
"self": 184.01663363599687
},
"steps_from_proto": {
"total": 33.662210907005374,
"count": 18196,
"is_parallel": true,
"self": 6.442766601000585,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.21944430600479,
"count": 181960,
"is_parallel": true,
"self": 27.21944430600479
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.739999998397252e-05,
"count": 1,
"self": 8.739999998397252e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 450.2009048899723,
"count": 716469,
"is_parallel": true,
"self": 14.514311836031084,
"children": {
"process_trajectory": {
"total": 249.15554410894015,
"count": 716469,
"is_parallel": true,
"self": 248.49703687594013,
"children": {
"RLTrainer._checkpoint": {
"total": 0.658507233000023,
"count": 4,
"is_parallel": true,
"self": 0.658507233000023
}
}
},
"_update_policy": {
"total": 186.5310489450011,
"count": 90,
"is_parallel": true,
"self": 56.69927696900595,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.83177197599514,
"count": 4587,
"is_parallel": true,
"self": 129.83177197599514
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08829407999996874,
"count": 1,
"self": 0.0010330489999432757,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08726103100002547,
"count": 1,
"self": 0.08726103100002547
}
}
}
}
}
}
}