xianbin's picture
First Push
b1aebc2
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9090112447738647,
"min": 0.9090112447738647,
"max": 2.86517596244812,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8669.240234375,
"min": 8669.240234375,
"max": 29405.30078125,
"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": 13.181597709655762,
"min": 0.30136173963546753,
"max": 13.181597709655762,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2570.41162109375,
"min": 58.46417999267578,
"max": 2661.236083984375,
"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": 0.06264865187689543,
"min": 0.06264865187689543,
"max": 0.07758081663424117,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2505946075075817,
"min": 0.2505946075075817,
"max": 0.3580031972949156,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.24553264304995537,
"min": 0.11562358169455775,
"max": 0.27698413786642695,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9821305721998215,
"min": 0.462494326778231,
"max": 1.3487743469429951,
"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": 26.181818181818183,
"min": 3.227272727272727,
"max": 26.181818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1152.0,
"min": 142.0,
"max": 1423.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.181818181818183,
"min": 3.227272727272727,
"max": 26.181818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1152.0,
"min": 142.0,
"max": 1423.0,
"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": "1690438041",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1690438506"
},
"total": 464.86998396099995,
"count": 1,
"self": 0.79586097899994,
"children": {
"run_training.setup": {
"total": 0.03450960399999303,
"count": 1,
"self": 0.03450960399999303
},
"TrainerController.start_learning": {
"total": 464.039613378,
"count": 1,
"self": 0.5434768879929379,
"children": {
"TrainerController._reset_env": {
"total": 6.381450057999984,
"count": 1,
"self": 6.381450057999984
},
"TrainerController.advance": {
"total": 456.7938649860071,
"count": 18228,
"self": 0.27411866600323265,
"children": {
"env_step": {
"total": 456.5197463200039,
"count": 18228,
"self": 329.29075268299937,
"children": {
"SubprocessEnvManager._take_step": {
"total": 126.9602359700043,
"count": 18228,
"self": 1.7368356889980419,
"children": {
"TorchPolicy.evaluate": {
"total": 125.22340028100626,
"count": 18228,
"self": 125.22340028100626
}
}
},
"workers": {
"total": 0.26875766700021586,
"count": 18228,
"self": 0.0,
"children": {
"worker_root": {
"total": 462.4989564229953,
"count": 18228,
"is_parallel": true,
"self": 221.50046736700148,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005280617999972037,
"count": 1,
"is_parallel": true,
"self": 0.0037769549998643015,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015036630001077356,
"count": 10,
"is_parallel": true,
"self": 0.0015036630001077356
}
}
},
"UnityEnvironment.step": {
"total": 0.06858467399996471,
"count": 1,
"is_parallel": true,
"self": 0.0006158249999543841,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004091310000262638,
"count": 1,
"is_parallel": true,
"self": 0.0004091310000262638
},
"communicator.exchange": {
"total": 0.06544912399999703,
"count": 1,
"is_parallel": true,
"self": 0.06544912399999703
},
"steps_from_proto": {
"total": 0.0021105939999870316,
"count": 1,
"is_parallel": true,
"self": 0.0005255649999185152,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015850290000685163,
"count": 10,
"is_parallel": true,
"self": 0.0015850290000685163
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 240.99848905599384,
"count": 18227,
"is_parallel": true,
"self": 10.171109658981777,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.188103327003262,
"count": 18227,
"is_parallel": true,
"self": 5.188103327003262
},
"communicator.exchange": {
"total": 191.13484369500242,
"count": 18227,
"is_parallel": true,
"self": 191.13484369500242
},
"steps_from_proto": {
"total": 34.50443237500639,
"count": 18227,
"is_parallel": true,
"self": 6.33509328400379,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.1693390910026,
"count": 182270,
"is_parallel": true,
"self": 28.1693390910026
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001213259999985894,
"count": 1,
"self": 0.0001213259999985894,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 453.41834320696546,
"count": 409745,
"is_parallel": true,
"self": 9.391447668922183,
"children": {
"process_trajectory": {
"total": 249.33335258204283,
"count": 409745,
"is_parallel": true,
"self": 245.94825405904282,
"children": {
"RLTrainer._checkpoint": {
"total": 3.3850985230000106,
"count": 4,
"is_parallel": true,
"self": 3.3850985230000106
}
}
},
"_update_policy": {
"total": 194.69354295600044,
"count": 90,
"is_parallel": true,
"self": 69.47795093300078,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.21559202299966,
"count": 4587,
"is_parallel": true,
"self": 125.21559202299966
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.3207001199999695,
"count": 1,
"self": 0.0031963339999947493,
"children": {
"RLTrainer._checkpoint": {
"total": 0.31750378599997475,
"count": 1,
"self": 0.31750378599997475
}
}
}
}
}
}
}