misza222's picture
First Push
d119b60
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.4800318479537964,
"min": 1.4800318479537964,
"max": 2.8810667991638184,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 12780.0751953125,
"min": 12780.0751953125,
"max": 37269.48046875,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199952.0,
"min": 9984.0,
"max": 199952.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199952.0,
"min": 9984.0,
"max": 199952.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 11.172700881958008,
"min": 0.2355472296476364,
"max": 11.172700881958008,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2178.6767578125,
"min": 36.74536895751953,
"max": 2178.6767578125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06875877716798891,
"min": 0.06612287850170302,
"max": 0.07470938909990603,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27503510867195563,
"min": 0.2644915140068121,
"max": 0.37354694549953016,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22732396122049905,
"min": 0.09633786856041601,
"max": 0.2782184243813961,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9092958448819962,
"min": 0.38535147424166405,
"max": 1.3737178864687973,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.389097537000013e-06,
"min": 7.389097537000013e-06,
"max": 0.00029208000264,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.955639014800005e-05,
"min": 2.955639014800005e-05,
"max": 0.0013876680374439998,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10246300000000001,
"min": 0.10246300000000001,
"max": 0.19736,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.40985200000000005,
"min": 0.40985200000000005,
"max": 0.9625560000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001329037000000002,
"min": 0.0001329037000000002,
"max": 0.004868264,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005316148000000008,
"min": 0.0005316148000000008,
"max": 0.023131544400000002,
"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
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 19
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 6567.0,
"max": 15323.0,
"count": 19
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 22.59090909090909,
"min": 3.659090909090909,
"max": 22.59090909090909,
"count": 19
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 994.0,
"min": 161.0,
"max": 1210.0,
"count": 19
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 22.59090909090909,
"min": 3.659090909090909,
"max": 22.59090909090909,
"count": 19
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 994.0,
"min": 161.0,
"max": 1210.0,
"count": 19
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1674138316",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --num-envs=10 --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674138632"
},
"total": 316.54353232299997,
"count": 1,
"self": 1.9799672190000024,
"children": {
"run_training.setup": {
"total": 0.1949375130000135,
"count": 1,
"self": 0.1949375130000135
},
"TrainerController.start_learning": {
"total": 314.36862759099995,
"count": 1,
"self": 0.19449614599932374,
"children": {
"TrainerController._reset_env": {
"total": 12.676022120000027,
"count": 1,
"self": 12.676022120000027
},
"TrainerController.advance": {
"total": 301.3814781470007,
"count": 2331,
"self": 0.0545158359961988,
"children": {
"env_step": {
"total": 301.3269623110045,
"count": 2331,
"self": 116.32193505399982,
"children": {
"SubprocessEnvManager._take_step": {
"total": 184.7944313690008,
"count": 18465,
"self": 2.2512006140066205,
"children": {
"TorchPolicy.evaluate": {
"total": 182.54323075499417,
"count": 18465,
"self": 39.01350742099578,
"children": {
"TorchPolicy.sample_actions": {
"total": 143.5297233339984,
"count": 18465,
"self": 143.5297233339984
}
}
}
}
},
"workers": {
"total": 0.21059588800386564,
"count": 2331,
"self": 0.0,
"children": {
"worker_root": {
"total": 3138.3121088859934,
"count": 18464,
"is_parallel": true,
"self": 2798.198358782991,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.03162055200004943,
"count": 10,
"is_parallel": true,
"self": 0.011684575999709068,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.01993597600034036,
"count": 100,
"is_parallel": true,
"self": 0.01993597600034036
}
}
},
"UnityEnvironment.step": {
"total": 0.5055241920000526,
"count": 10,
"is_parallel": true,
"self": 0.009800306000158798,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0030178359999695203,
"count": 10,
"is_parallel": true,
"self": 0.0030178359999695203
},
"communicator.exchange": {
"total": 0.47436315299984244,
"count": 10,
"is_parallel": true,
"self": 0.47436315299984244
},
"steps_from_proto": {
"total": 0.018342897000081848,
"count": 10,
"is_parallel": true,
"self": 0.004278560000273046,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.014064336999808802,
"count": 100,
"is_parallel": true,
"self": 0.014064336999808802
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 340.11375010300253,
"count": 18454,
"is_parallel": true,
"self": 10.205676438003309,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.212662117997411,
"count": 18454,
"is_parallel": true,
"self": 5.212662117997411
},
"communicator.exchange": {
"total": 285.422573612999,
"count": 18454,
"is_parallel": true,
"self": 285.422573612999
},
"steps_from_proto": {
"total": 39.27283793400284,
"count": 18454,
"is_parallel": true,
"self": 10.58265081601786,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.690187117984976,
"count": 184540,
"is_parallel": true,
"self": 28.690187117984976
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.521999994722137e-05,
"count": 1,
"self": 4.521999994722137e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 299.3901322760056,
"count": 201838,
"is_parallel": true,
"self": 5.57299689298992,
"children": {
"process_trajectory": {
"total": 145.1297867060161,
"count": 201838,
"is_parallel": true,
"self": 144.333614768016,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7961719380001,
"count": 4,
"is_parallel": true,
"self": 0.7961719380001
}
}
},
"_update_policy": {
"total": 148.6873486769996,
"count": 89,
"is_parallel": true,
"self": 46.22865886799974,
"children": {
"TorchPPOOptimizer.update": {
"total": 102.45868980899985,
"count": 4536,
"is_parallel": true,
"self": 102.45868980899985
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11658595799997329,
"count": 1,
"self": 0.000865122000050178,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11572083599992311,
"count": 1,
"self": 0.11572083599992311
}
}
}
}
}
}
}