keyblade95's picture
First Push
4c0bd13
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8214545845985413,
"min": 0.8214545845985413,
"max": 2.8529951572418213,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7843.24853515625,
"min": 7843.24853515625,
"max": 29217.5234375,
"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": 12.966485977172852,
"min": 0.33994850516319275,
"max": 12.966485977172852,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2528.46484375,
"min": 65.95001220703125,
"max": 2622.72998046875,
"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": 0.06930968769815722,
"min": 0.06183407152325256,
"max": 0.07535613584503367,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2772387507926289,
"min": 0.24733628609301023,
"max": 0.3504740401014501,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21244041899255675,
"min": 0.10282655625818662,
"max": 0.2779879297111548,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.849761675970227,
"min": 0.4113062250327465,
"max": 1.3899396485557742,
"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": 25.15909090909091,
"min": 3.1136363636363638,
"max": 25.436363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1107.0,
"min": 137.0,
"max": 1399.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.15909090909091,
"min": 3.1136363636363638,
"max": 25.436363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1107.0,
"min": 137.0,
"max": 1399.0,
"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": "1675086575",
"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": "1675087018"
},
"total": 442.77191859500005,
"count": 1,
"self": 0.39532696400010536,
"children": {
"run_training.setup": {
"total": 0.1093207879999909,
"count": 1,
"self": 0.1093207879999909
},
"TrainerController.start_learning": {
"total": 442.26727084299995,
"count": 1,
"self": 0.481566367993878,
"children": {
"TrainerController._reset_env": {
"total": 10.222931513999981,
"count": 1,
"self": 10.222931513999981
},
"TrainerController.advance": {
"total": 431.437812671006,
"count": 18200,
"self": 0.2736704110004098,
"children": {
"env_step": {
"total": 431.1641422600056,
"count": 18200,
"self": 279.4243764020121,
"children": {
"SubprocessEnvManager._take_step": {
"total": 151.46575353599144,
"count": 18200,
"self": 1.4495857349873518,
"children": {
"TorchPolicy.evaluate": {
"total": 150.0161678010041,
"count": 18200,
"self": 33.54731601099809,
"children": {
"TorchPolicy.sample_actions": {
"total": 116.468851790006,
"count": 18200,
"self": 116.468851790006
}
}
}
}
},
"workers": {
"total": 0.2740123220020223,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 441.06816575999267,
"count": 18200,
"is_parallel": true,
"self": 214.55549987399002,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.011175646000026518,
"count": 1,
"is_parallel": true,
"self": 0.005493984000111141,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005681661999915377,
"count": 10,
"is_parallel": true,
"self": 0.005681661999915377
}
}
},
"UnityEnvironment.step": {
"total": 0.04611295899997003,
"count": 1,
"is_parallel": true,
"self": 0.0007504370000219751,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037866399998165434,
"count": 1,
"is_parallel": true,
"self": 0.00037866399998165434
},
"communicator.exchange": {
"total": 0.043068523999977515,
"count": 1,
"is_parallel": true,
"self": 0.043068523999977515
},
"steps_from_proto": {
"total": 0.0019153339999888885,
"count": 1,
"is_parallel": true,
"self": 0.0004367899999238034,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014785440000650851,
"count": 10,
"is_parallel": true,
"self": 0.0014785440000650851
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 226.51266588600265,
"count": 18199,
"is_parallel": true,
"self": 8.547930658013058,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.210108624002999,
"count": 18199,
"is_parallel": true,
"self": 5.210108624002999
},
"communicator.exchange": {
"total": 180.8157255129937,
"count": 18199,
"is_parallel": true,
"self": 180.8157255129937
},
"steps_from_proto": {
"total": 31.938901090992886,
"count": 18199,
"is_parallel": true,
"self": 6.807497044020238,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.131404046972648,
"count": 181990,
"is_parallel": true,
"self": 25.131404046972648
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.6006000047782436e-05,
"count": 1,
"self": 4.6006000047782436e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 428.3052692980282,
"count": 345314,
"is_parallel": true,
"self": 9.613889753020317,
"children": {
"process_trajectory": {
"total": 247.13987100400817,
"count": 345314,
"is_parallel": true,
"self": 246.39870832000815,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7411626840000167,
"count": 4,
"is_parallel": true,
"self": 0.7411626840000167
}
}
},
"_update_policy": {
"total": 171.5515085409997,
"count": 90,
"is_parallel": true,
"self": 41.18585396800131,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.36565457299838,
"count": 4587,
"is_parallel": true,
"self": 130.36565457299838
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12491428400005589,
"count": 1,
"self": 0.0008270820000007006,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12408720200005519,
"count": 1,
"self": 0.12408720200005519
}
}
}
}
}
}
}