hmatzner's picture
Trained model finished
3046f03
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9732351303100586,
"min": 0.9732351303100586,
"max": 2.864677667617798,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9292.44921875,
"min": 9292.44921875,
"max": 29400.1875,
"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": 12.881447792053223,
"min": 0.4046575725078583,
"max": 12.881447792053223,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2511.88232421875,
"min": 78.50357055664062,
"max": 2604.93359375,
"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": 0.07010801168008567,
"min": 0.06210976669122008,
"max": 0.07658706022330614,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28043204672034266,
"min": 0.2484390667648803,
"max": 0.35894714032674174,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1984784366453395,
"min": 0.1076309260633756,
"max": 0.2947612062973135,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.793913746581358,
"min": 0.4305237042535024,
"max": 1.4221170302115236,
"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": 25.704545454545453,
"min": 3.022727272727273,
"max": 25.704545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1131.0,
"min": 133.0,
"max": 1379.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.704545454545453,
"min": 3.022727272727273,
"max": 25.704545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1131.0,
"min": 133.0,
"max": 1379.0,
"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": "1678883467",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "1678883922"
},
"total": 454.65633954400005,
"count": 1,
"self": 0.43267644600007316,
"children": {
"run_training.setup": {
"total": 0.10934029800000644,
"count": 1,
"self": 0.10934029800000644
},
"TrainerController.start_learning": {
"total": 454.11432279999997,
"count": 1,
"self": 0.5104520609979772,
"children": {
"TrainerController._reset_env": {
"total": 9.398708162000048,
"count": 1,
"self": 9.398708162000048
},
"TrainerController.advance": {
"total": 444.0781598790021,
"count": 18201,
"self": 0.2798188370047683,
"children": {
"env_step": {
"total": 443.79834104199733,
"count": 18201,
"self": 320.6503926999984,
"children": {
"SubprocessEnvManager._take_step": {
"total": 122.89702657000146,
"count": 18201,
"self": 2.4912557419936547,
"children": {
"TorchPolicy.evaluate": {
"total": 120.4057708280078,
"count": 18201,
"self": 120.4057708280078
}
}
},
"workers": {
"total": 0.25092177199746857,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 452.71786499500047,
"count": 18201,
"is_parallel": true,
"self": 219.27604701099722,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005947079000065969,
"count": 1,
"is_parallel": true,
"self": 0.004334945000096013,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016121339999699558,
"count": 10,
"is_parallel": true,
"self": 0.0016121339999699558
}
}
},
"UnityEnvironment.step": {
"total": 0.04313698700002533,
"count": 1,
"is_parallel": true,
"self": 0.0005993650000846173,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039130600009684713,
"count": 1,
"is_parallel": true,
"self": 0.00039130600009684713
},
"communicator.exchange": {
"total": 0.04020855599992501,
"count": 1,
"is_parallel": true,
"self": 0.04020855599992501
},
"steps_from_proto": {
"total": 0.0019377599999188533,
"count": 1,
"is_parallel": true,
"self": 0.00040913500015449245,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015286249997643608,
"count": 10,
"is_parallel": true,
"self": 0.0015286249997643608
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 233.44181798400325,
"count": 18200,
"is_parallel": true,
"self": 9.507946862010158,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.051902695996773,
"count": 18200,
"is_parallel": true,
"self": 5.051902695996773
},
"communicator.exchange": {
"total": 188.60152605498627,
"count": 18200,
"is_parallel": true,
"self": 188.60152605498627
},
"steps_from_proto": {
"total": 30.280442371010054,
"count": 18200,
"is_parallel": true,
"self": 5.934596826019401,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.345845544990652,
"count": 182000,
"is_parallel": true,
"self": 24.345845544990652
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016252999989774253,
"count": 1,
"self": 0.00016252999989774253,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 440.72651718696375,
"count": 394724,
"is_parallel": true,
"self": 9.84685972297359,
"children": {
"process_trajectory": {
"total": 244.98808901199118,
"count": 394724,
"is_parallel": true,
"self": 244.25348222999116,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7346067820000144,
"count": 4,
"is_parallel": true,
"self": 0.7346067820000144
}
}
},
"_update_policy": {
"total": 185.89156845199898,
"count": 90,
"is_parallel": true,
"self": 68.9819812189993,
"children": {
"TorchPPOOptimizer.update": {
"total": 116.90958723299968,
"count": 4587,
"is_parallel": true,
"self": 116.90958723299968
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12684016799994424,
"count": 1,
"self": 0.0008413819998622785,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12599878600008196,
"count": 1,
"self": 0.12599878600008196
}
}
}
}
}
}
}