jaymanvirk's picture
initial commit
41ec415 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.751897931098938,
"min": 0.751897931098938,
"max": 2.865082025527954,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7187.39208984375,
"min": 7187.39208984375,
"max": 29372.8203125,
"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": 12.96750259399414,
"min": 0.2719246447086334,
"max": 12.96750259399414,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2528.6630859375,
"min": 52.75338363647461,
"max": 2631.662109375,
"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": 0.0646194786034482,
"min": 0.06343484760168483,
"max": 0.07286038056116403,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2584779144137928,
"min": 0.258225917030644,
"max": 0.3643019028058202,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20491300654761932,
"min": 0.1177096348438485,
"max": 0.28706027292737774,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8196520261904773,
"min": 0.470838539375394,
"max": 1.4353013646368886,
"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": 25.318181818181817,
"min": 3.0681818181818183,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1114.0,
"min": 135.0,
"max": 1377.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.318181818181817,
"min": 3.0681818181818183,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1114.0,
"min": 135.0,
"max": 1377.0,
"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": "1715329133",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1715329597"
},
"total": 464.168778964,
"count": 1,
"self": 0.49031037299994296,
"children": {
"run_training.setup": {
"total": 0.05380124600003455,
"count": 1,
"self": 0.05380124600003455
},
"TrainerController.start_learning": {
"total": 463.62466734500003,
"count": 1,
"self": 0.5608698130031371,
"children": {
"TrainerController._reset_env": {
"total": 2.7724802049999653,
"count": 1,
"self": 2.7724802049999653
},
"TrainerController.advance": {
"total": 460.20260996899697,
"count": 18200,
"self": 0.2671021759925907,
"children": {
"env_step": {
"total": 459.9355077930044,
"count": 18200,
"self": 300.86199906399816,
"children": {
"SubprocessEnvManager._take_step": {
"total": 158.79359893300602,
"count": 18200,
"self": 1.5162840500074708,
"children": {
"TorchPolicy.evaluate": {
"total": 157.27731488299855,
"count": 18200,
"self": 157.27731488299855
}
}
},
"workers": {
"total": 0.2799097960001973,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 462.44677085999524,
"count": 18200,
"is_parallel": true,
"self": 233.36207169499005,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005292131000032896,
"count": 1,
"is_parallel": true,
"self": 0.0037196729999777745,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015724580000551214,
"count": 10,
"is_parallel": true,
"self": 0.0015724580000551214
}
}
},
"UnityEnvironment.step": {
"total": 0.03809536999995089,
"count": 1,
"is_parallel": true,
"self": 0.0007806749999872409,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005567939999764349,
"count": 1,
"is_parallel": true,
"self": 0.0005567939999764349
},
"communicator.exchange": {
"total": 0.03409534399997938,
"count": 1,
"is_parallel": true,
"self": 0.03409534399997938
},
"steps_from_proto": {
"total": 0.002662557000007837,
"count": 1,
"is_parallel": true,
"self": 0.0005982860000131041,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002064270999994733,
"count": 10,
"is_parallel": true,
"self": 0.002064270999994733
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 229.0846991650052,
"count": 18199,
"is_parallel": true,
"self": 10.346418137989417,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.570840322009872,
"count": 18199,
"is_parallel": true,
"self": 5.570840322009872
},
"communicator.exchange": {
"total": 178.33354111100414,
"count": 18199,
"is_parallel": true,
"self": 178.33354111100414
},
"steps_from_proto": {
"total": 34.833899594001764,
"count": 18199,
"is_parallel": true,
"self": 6.58370309400118,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.250196500000584,
"count": 181990,
"is_parallel": true,
"self": 28.250196500000584
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014976299996760645,
"count": 1,
"self": 0.00014976299996760645,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 454.45250587899955,
"count": 682684,
"is_parallel": true,
"self": 14.961836843008541,
"children": {
"process_trajectory": {
"total": 251.17402132899144,
"count": 682684,
"is_parallel": true,
"self": 250.35217951799154,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8218418109998993,
"count": 4,
"is_parallel": true,
"self": 0.8218418109998993
}
}
},
"_update_policy": {
"total": 188.31664770699956,
"count": 90,
"is_parallel": true,
"self": 61.078394768993576,
"children": {
"TorchPPOOptimizer.update": {
"total": 127.23825293800599,
"count": 4587,
"is_parallel": true,
"self": 127.23825293800599
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08855759499999749,
"count": 1,
"self": 0.0009996569999657368,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08755793800003175,
"count": 1,
"self": 0.08755793800003175
}
}
}
}
}
}
}