eyechen's picture
First Push
b3a8851
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9754799604415894,
"min": 0.9754799604415894,
"max": 2.8609485626220703,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9367.5341796875,
"min": 9367.5341796875,
"max": 29393.38671875,
"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": 12.72630500793457,
"min": 0.4138834774494171,
"max": 12.72630500793457,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2481.62939453125,
"min": 80.29339599609375,
"max": 2592.5283203125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0753849941629953,
"min": 0.058183507578260275,
"max": 0.0753849941629953,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3015399766519812,
"min": 0.27144360273400797,
"max": 0.36497968230989997,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20449146562639406,
"min": 0.13361799974204497,
"max": 0.271368849584285,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8179658625055762,
"min": 0.5344719989681799,
"max": 1.2850568022798088,
"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": 24.954545454545453,
"min": 3.7045454545454546,
"max": 25.522727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1098.0,
"min": 163.0,
"max": 1386.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.954545454545453,
"min": 3.7045454545454546,
"max": 25.522727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1098.0,
"min": 163.0,
"max": 1386.0,
"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": "1682277725",
"python_version": "3.10.6 (main, Nov 14 2022, 16:10:14) [GCC 11.3.0]",
"command_line_arguments": "/home/owner/Documents/venv/unit5_deeprl/bin/mlagents-learn --force ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"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": "1682278029"
},
"total": 304.04760746399995,
"count": 1,
"self": 0.21846068399997876,
"children": {
"run_training.setup": {
"total": 0.013335617999985061,
"count": 1,
"self": 0.013335617999985061
},
"TrainerController.start_learning": {
"total": 303.815811162,
"count": 1,
"self": 0.39285411400248904,
"children": {
"TrainerController._reset_env": {
"total": 3.5483437210000375,
"count": 1,
"self": 3.5483437210000375
},
"TrainerController.advance": {
"total": 299.7664397019974,
"count": 18207,
"self": 0.18855063100198777,
"children": {
"env_step": {
"total": 299.5778890709954,
"count": 18207,
"self": 222.58983684400044,
"children": {
"SubprocessEnvManager._take_step": {
"total": 76.77820888499264,
"count": 18207,
"self": 0.9949836969938701,
"children": {
"TorchPolicy.evaluate": {
"total": 75.78322518799877,
"count": 18207,
"self": 75.78322518799877
}
}
},
"workers": {
"total": 0.2098433420023298,
"count": 18207,
"self": 0.0,
"children": {
"worker_root": {
"total": 303.2565785269908,
"count": 18207,
"is_parallel": true,
"self": 145.7901963609865,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001919820000011896,
"count": 1,
"is_parallel": true,
"self": 0.0004232379999962177,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014965820000156782,
"count": 10,
"is_parallel": true,
"self": 0.0014965820000156782
}
}
},
"UnityEnvironment.step": {
"total": 0.024837326000010762,
"count": 1,
"is_parallel": true,
"self": 0.0007657859999312677,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005195650000473506,
"count": 1,
"is_parallel": true,
"self": 0.0005195650000473506
},
"communicator.exchange": {
"total": 0.021384006999994654,
"count": 1,
"is_parallel": true,
"self": 0.021384006999994654
},
"steps_from_proto": {
"total": 0.00216796800003749,
"count": 1,
"is_parallel": true,
"self": 0.0003217489999656209,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018462190000718692,
"count": 10,
"is_parallel": true,
"self": 0.0018462190000718692
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 157.46638216600428,
"count": 18206,
"is_parallel": true,
"self": 7.47759051499844,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.436521702010225,
"count": 18206,
"is_parallel": true,
"self": 3.436521702010225
},
"communicator.exchange": {
"total": 124.44005488999568,
"count": 18206,
"is_parallel": true,
"self": 124.44005488999568
},
"steps_from_proto": {
"total": 22.112215058999936,
"count": 18206,
"is_parallel": true,
"self": 3.9743306800066875,
"children": {
"_process_rank_one_or_two_observation": {
"total": 18.13788437899325,
"count": 182060,
"is_parallel": true,
"self": 18.13788437899325
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.67600000699531e-05,
"count": 1,
"self": 7.67600000699531e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 299.2395181739892,
"count": 185622,
"is_parallel": true,
"self": 2.2431674949830267,
"children": {
"process_trajectory": {
"total": 171.89699017600594,
"count": 185622,
"is_parallel": true,
"self": 171.30486343300595,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5921267429999943,
"count": 4,
"is_parallel": true,
"self": 0.5921267429999943
}
}
},
"_update_policy": {
"total": 125.09936050300024,
"count": 90,
"is_parallel": true,
"self": 33.393523930006836,
"children": {
"TorchPPOOptimizer.update": {
"total": 91.7058365729934,
"count": 4587,
"is_parallel": true,
"self": 91.7058365729934
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10809686499999316,
"count": 1,
"self": 0.0006581320000123014,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10743873299998086,
"count": 1,
"self": 0.10743873299998086
}
}
}
}
}
}
}