Menoua Keshishian
SnowballTarget rev1
113b365
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7859947681427002,
"min": 0.7859947681427002,
"max": 2.8318145275115967,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 19686.810546875,
"min": 19619.8125,
"max": 72517.109375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 24968.0,
"max": 499976.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 24968.0,
"max": 499976.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.6461763381958,
"min": 0.51382976770401,
"max": 13.651637077331543,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 6904.96533203125,
"min": 254.8595733642578,
"max": 6904.96533203125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 26268.0,
"min": 24079.0,
"max": 26268.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.62878787878788,
"min": 4.553719008264463,
"max": 26.94214876033058,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 3515.0,
"min": 551.0,
"max": 3515.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.62878787878788,
"min": 4.553719008264463,
"max": 26.94214876033058,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 3515.0,
"min": 551.0,
"max": 3515.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.04688683807957549,
"min": 0.04605300494353096,
"max": 0.05252575257186525,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28132102847745294,
"min": 0.23125561833034688,
"max": 0.3151545154311915,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17358876920603458,
"min": 0.15230694262986527,
"max": 0.29392827034386154,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.0415326152362074,
"min": 0.7615347131493264,
"max": 1.7635696220631694,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.332897222400001e-06,
"min": 8.332897222400001e-06,
"max": 0.0002921328026223999,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 4.9997383334400005e-05,
"min": 4.9997383334400005e-05,
"max": 0.0016656768447744,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10277760000000002,
"min": 0.10277760000000002,
"max": 0.19737760000000001,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.6166656000000001,
"min": 0.538088,
"max": 1.1552256,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014860224000000006,
"min": 0.00014860224000000006,
"max": 0.004869142240000001,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0008916134400000003,
"min": 0.0008916134400000003,
"max": 0.027765757439999997,
"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": "1676668558",
"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 --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": "1676669713"
},
"total": 1155.0211820390002,
"count": 1,
"self": 0.920332836000398,
"children": {
"run_training.setup": {
"total": 0.24488344599990342,
"count": 1,
"self": 0.24488344599990342
},
"TrainerController.start_learning": {
"total": 1153.855965757,
"count": 1,
"self": 1.3387109529874124,
"children": {
"TrainerController._reset_env": {
"total": 10.319778841000016,
"count": 1,
"self": 10.319778841000016
},
"TrainerController.advance": {
"total": 1141.9655888990128,
"count": 45498,
"self": 0.673059967034078,
"children": {
"env_step": {
"total": 1141.2925289319787,
"count": 45498,
"self": 796.705685053968,
"children": {
"SubprocessEnvManager._take_step": {
"total": 343.90887735505567,
"count": 45498,
"self": 3.671479174022352,
"children": {
"TorchPolicy.evaluate": {
"total": 340.2373981810333,
"count": 45498,
"self": 73.24613573905708,
"children": {
"TorchPolicy.sample_actions": {
"total": 266.99126244197623,
"count": 45498,
"self": 266.99126244197623
}
}
}
}
},
"workers": {
"total": 0.6779665229551028,
"count": 45498,
"self": 0.0,
"children": {
"worker_root": {
"total": 1150.413129788012,
"count": 45498,
"is_parallel": true,
"self": 546.1572656300639,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008956384000157414,
"count": 1,
"is_parallel": true,
"self": 0.0028390660004333768,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.006117317999724037,
"count": 10,
"is_parallel": true,
"self": 0.006117317999724037
}
}
},
"UnityEnvironment.step": {
"total": 0.041772388000026694,
"count": 1,
"is_parallel": true,
"self": 0.0006145270001525205,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003015119998508453,
"count": 1,
"is_parallel": true,
"self": 0.0003015119998508453
},
"communicator.exchange": {
"total": 0.03885804099991219,
"count": 1,
"is_parallel": true,
"self": 0.03885804099991219
},
"steps_from_proto": {
"total": 0.0019983080001111375,
"count": 1,
"is_parallel": true,
"self": 0.0004486510001697752,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015496569999413623,
"count": 10,
"is_parallel": true,
"self": 0.0015496569999413623
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 604.255864157948,
"count": 45497,
"is_parallel": true,
"self": 24.349677040849656,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 13.116226514046957,
"count": 45497,
"is_parallel": true,
"self": 13.116226514046957
},
"communicator.exchange": {
"total": 487.92493951101005,
"count": 45497,
"is_parallel": true,
"self": 487.92493951101005
},
"steps_from_proto": {
"total": 78.86502109204139,
"count": 45497,
"is_parallel": true,
"self": 17.032292121078626,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.83272897096276,
"count": 454970,
"is_parallel": true,
"self": 61.83272897096276
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001355350000267208,
"count": 1,
"self": 0.0001355350000267208,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1130.3117287000566,
"count": 1298724,
"is_parallel": true,
"self": 35.026572685793326,
"children": {
"process_trajectory": {
"total": 792.352845453262,
"count": 1298724,
"is_parallel": true,
"self": 789.188015009262,
"children": {
"RLTrainer._checkpoint": {
"total": 3.1648304440000175,
"count": 10,
"is_parallel": true,
"self": 3.1648304440000175
}
}
},
"_update_policy": {
"total": 302.93231056100126,
"count": 113,
"is_parallel": true,
"self": 148.85505404900186,
"children": {
"TorchPPOOptimizer.update": {
"total": 154.0772565119994,
"count": 5760,
"is_parallel": true,
"self": 154.0772565119994
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.23175152899966633,
"count": 1,
"self": 0.001629219999358611,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23012230900030772,
"count": 1,
"self": 0.23012230900030772
}
}
}
}
}
}
}