rabeeqasem's picture
First Push
5ba51ad verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9832627773284912,
"min": 0.9832627773284912,
"max": 2.8530046939849854,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9344.9296875,
"min": 9344.9296875,
"max": 29123.470703125,
"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": 13.034635543823242,
"min": 0.4087042212486267,
"max": 13.034635543823242,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2541.75390625,
"min": 79.28861999511719,
"max": 2628.4931640625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07617389073757472,
"min": 0.06292744302710145,
"max": 0.07617389073757472,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.30469556295029887,
"min": 0.2517097721084058,
"max": 0.3693887275750931,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1887760605005657,
"min": 0.13152991258881658,
"max": 0.29155188717094127,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7551042420022628,
"min": 0.5261196503552663,
"max": 1.4577594358547064,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.931818181818183,
"min": 3.1818181818181817,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1141.0,
"min": 140.0,
"max": 1429.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.931818181818183,
"min": 3.1818181818181817,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1141.0,
"min": 140.0,
"max": 1429.0,
"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": "1758375801",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1758376184"
},
"total": 382.828819208,
"count": 1,
"self": 0.32138930799999343,
"children": {
"run_training.setup": {
"total": 0.022585176000006868,
"count": 1,
"self": 0.022585176000006868
},
"TrainerController.start_learning": {
"total": 382.484844724,
"count": 1,
"self": 0.3982075290035709,
"children": {
"TrainerController._reset_env": {
"total": 2.051765064000051,
"count": 1,
"self": 2.051765064000051
},
"TrainerController.advance": {
"total": 379.9568273909964,
"count": 18192,
"self": 0.3782540850025953,
"children": {
"env_step": {
"total": 265.94932167800414,
"count": 18192,
"self": 199.61572227099998,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.09952725899484,
"count": 18192,
"self": 1.2440579109952523,
"children": {
"TorchPolicy.evaluate": {
"total": 64.85546934799959,
"count": 18192,
"self": 64.85546934799959
}
}
},
"workers": {
"total": 0.23407214800931797,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 381.626447190013,
"count": 18192,
"is_parallel": true,
"self": 206.20256573801896,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00207612600001994,
"count": 1,
"is_parallel": true,
"self": 0.0006466069997941304,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014295190002258096,
"count": 10,
"is_parallel": true,
"self": 0.0014295190002258096
}
}
},
"UnityEnvironment.step": {
"total": 0.026431357999967986,
"count": 1,
"is_parallel": true,
"self": 0.00039001900006496726,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002740549999771247,
"count": 1,
"is_parallel": true,
"self": 0.0002740549999771247
},
"communicator.exchange": {
"total": 0.024464686999976948,
"count": 1,
"is_parallel": true,
"self": 0.024464686999976948
},
"steps_from_proto": {
"total": 0.0013025969999489462,
"count": 1,
"is_parallel": true,
"self": 0.0002704080000057729,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010321889999431733,
"count": 10,
"is_parallel": true,
"self": 0.0010321889999431733
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 175.42388145199402,
"count": 18191,
"is_parallel": true,
"self": 6.017049203007446,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.3049217559956787,
"count": 18191,
"is_parallel": true,
"self": 3.3049217559956787
},
"communicator.exchange": {
"total": 146.4354171979935,
"count": 18191,
"is_parallel": true,
"self": 146.4354171979935
},
"steps_from_proto": {
"total": 19.666493294997395,
"count": 18191,
"is_parallel": true,
"self": 3.801509660970737,
"children": {
"_process_rank_one_or_two_observation": {
"total": 15.864983634026657,
"count": 181910,
"is_parallel": true,
"self": 15.864983634026657
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 113.62925162798967,
"count": 18192,
"self": 0.5163473629794453,
"children": {
"process_trajectory": {
"total": 24.86855076101017,
"count": 18192,
"self": 24.513397901010194,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3551528599999756,
"count": 4,
"self": 0.3551528599999756
}
}
},
"_update_policy": {
"total": 88.24435350400006,
"count": 90,
"self": 35.7228254819978,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.52152802200226,
"count": 4587,
"self": 52.52152802200226
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1160000212839805e-06,
"count": 1,
"self": 1.1160000212839805e-06
},
"TrainerController._save_models": {
"total": 0.07804362399997444,
"count": 1,
"self": 0.0008299409998926421,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0772136830000818,
"count": 1,
"self": 0.0772136830000818
}
}
}
}
}
}
}