mehmetyigitrl's picture
Hyperparam Tuning
d948a70
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0179998874664307,
"min": 1.0179998874664307,
"max": 2.8816232681274414,
"count": 40
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10402.94140625,
"min": 9812.6806640625,
"max": 29669.193359375,
"count": 40
},
"SnowballTarget.Step.mean": {
"value": 399992.0,
"min": 9952.0,
"max": 399992.0,
"count": 40
},
"SnowballTarget.Step.sum": {
"value": 399992.0,
"min": 9952.0,
"max": 399992.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.216809272766113,
"min": 0.1776331067085266,
"max": 13.216809272766113,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2577.27783203125,
"min": 34.46082305908203,
"max": 2697.09765625,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.454545454545453,
"min": 2.659090909090909,
"max": 26.454545454545453,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1164.0,
"min": 117.0,
"max": 1447.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.454545454545453,
"min": 2.659090909090909,
"max": 26.454545454545453,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1164.0,
"min": 117.0,
"max": 1447.0,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.10018987917040553,
"min": 0.08981524619529783,
"max": 0.10747867187741328,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.20037975834081106,
"min": 0.17963049239059567,
"max": 0.31710270352892156,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1706300188111616,
"min": 0.07835130111641696,
"max": 0.2309948849716997,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.3412600376223232,
"min": 0.15670260223283392,
"max": 0.6929846549150991,
"count": 40
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.1440984280000024e-06,
"min": 3.1440984280000024e-06,
"max": 0.00019674400162800003,
"count": 40
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 6.288196856000005e-06,
"min": 6.288196856000005e-06,
"max": 0.0005473320263340001,
"count": 40
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10078600000000001,
"min": 0.10078600000000001,
"max": 0.14918600000000004,
"count": 40
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.20157200000000003,
"min": 0.20157200000000003,
"max": 0.4368329999999999,
"count": 40
},
"SnowballTarget.Policy.Beta.mean": {
"value": 8.844280000000007e-05,
"min": 8.844280000000007e-05,
"max": 0.0049187627999999995,
"count": 40
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00017688560000000015,
"min": 0.00017688560000000015,
"max": 0.0136859334,
"count": 40
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1679315038",
"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 --force",
"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": "1679316065"
},
"total": 1026.9627269110001,
"count": 1,
"self": 0.42386767400012104,
"children": {
"run_training.setup": {
"total": 0.1020579760001965,
"count": 1,
"self": 0.1020579760001965
},
"TrainerController.start_learning": {
"total": 1026.4368012609998,
"count": 1,
"self": 1.0849357309398329,
"children": {
"TrainerController._reset_env": {
"total": 6.8931366229999185,
"count": 1,
"self": 6.8931366229999185
},
"TrainerController.advance": {
"total": 1018.32177950206,
"count": 36406,
"self": 0.5312980311036881,
"children": {
"env_step": {
"total": 1017.7904814709564,
"count": 36406,
"self": 783.8077283260764,
"children": {
"SubprocessEnvManager._take_step": {
"total": 233.44474938392204,
"count": 36406,
"self": 4.75262694893172,
"children": {
"TorchPolicy.evaluate": {
"total": 228.69212243499032,
"count": 36406,
"self": 228.69212243499032
}
}
},
"workers": {
"total": 0.5380037609579631,
"count": 36406,
"self": 0.0,
"children": {
"worker_root": {
"total": 1023.3385514439997,
"count": 36406,
"is_parallel": true,
"self": 539.2328077109983,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002272190999974555,
"count": 1,
"is_parallel": true,
"self": 0.0007691100008742069,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001503080999100348,
"count": 10,
"is_parallel": true,
"self": 0.001503080999100348
}
}
},
"UnityEnvironment.step": {
"total": 0.03662252900039675,
"count": 1,
"is_parallel": true,
"self": 0.0005368560005081235,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004355089999990014,
"count": 1,
"is_parallel": true,
"self": 0.0004355089999990014
},
"communicator.exchange": {
"total": 0.033707068000239815,
"count": 1,
"is_parallel": true,
"self": 0.033707068000239815
},
"steps_from_proto": {
"total": 0.0019430959996498132,
"count": 1,
"is_parallel": true,
"self": 0.0003960139997616352,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001547081999888178,
"count": 10,
"is_parallel": true,
"self": 0.001547081999888178
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 484.1057437330014,
"count": 36405,
"is_parallel": true,
"self": 19.045695103150592,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 10.679216891955548,
"count": 36405,
"is_parallel": true,
"self": 10.679216891955548
},
"communicator.exchange": {
"total": 390.0623916369723,
"count": 36405,
"is_parallel": true,
"self": 390.0623916369723
},
"steps_from_proto": {
"total": 64.318440100923,
"count": 36405,
"is_parallel": true,
"self": 12.715820958037057,
"children": {
"_process_rank_one_or_two_observation": {
"total": 51.60261914288594,
"count": 364050,
"is_parallel": true,
"self": 51.60261914288594
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00020376600014060386,
"count": 1,
"self": 0.00020376600014060386,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1009.1185825531134,
"count": 1037330,
"is_parallel": true,
"self": 26.12768551106683,
"children": {
"process_trajectory": {
"total": 620.3641213020469,
"count": 1037330,
"is_parallel": true,
"self": 618.4720522820467,
"children": {
"RLTrainer._checkpoint": {
"total": 1.8920690200002355,
"count": 8,
"is_parallel": true,
"self": 1.8920690200002355
}
}
},
"_update_policy": {
"total": 362.62677573999963,
"count": 90,
"is_parallel": true,
"self": 121.65017745000205,
"children": {
"TorchPPOOptimizer.update": {
"total": 240.97659828999758,
"count": 18357,
"is_parallel": true,
"self": 240.97659828999758
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13674563899985515,
"count": 1,
"self": 0.0011115379998045682,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13563410100005058,
"count": 1,
"self": 0.13563410100005058
}
}
}
}
}
}
}