jovisaib's picture
First Push
e92a39a
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4665730893611908,
"min": 0.4665730893611908,
"max": 1.3950711488723755,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 14041.9833984375,
"min": 14041.9833984375,
"max": 42320.87890625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989975.0,
"min": 29952.0,
"max": 989975.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989975.0,
"min": 29952.0,
"max": 989975.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3984026312828064,
"min": -0.11583032459020615,
"max": 0.3984026312828064,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 106.37350463867188,
"min": -27.799278259277344,
"max": 106.37350463867188,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.11658787727355957,
"min": -0.046512670814991,
"max": 0.4706920385360718,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 31.128963470458984,
"min": -12.186319351196289,
"max": 111.55401611328125,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07064225843108336,
"min": 0.06550741524509816,
"max": 0.073899029968379,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9889916180351671,
"min": 0.46295109430853887,
"max": 1.0690346696452857,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014547538980314998,
"min": 8.727709265197231e-05,
"max": 0.01488236753616178,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.20366554572440998,
"min": 0.0009600480191716955,
"max": 0.20835314550626494,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.549468912114288e-06,
"min": 7.549468912114288e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010569256476960003,
"min": 0.00010569256476960003,
"max": 0.0031169527610158,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10251645714285716,
"min": 0.10251645714285716,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4352304000000002,
"min": 1.3886848,
"max": 2.2752733000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026139406857142867,
"min": 0.00026139406857142867,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003659516960000001,
"min": 0.003659516960000001,
"max": 0.10391452158000002,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01422286219894886,
"min": 0.01422286219894886,
"max": 0.501937747001648,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.19912007451057434,
"min": 0.19912007451057434,
"max": 3.513564109802246,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 461.53731343283584,
"min": 461.53731343283584,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30923.0,
"min": 15984.0,
"max": 32383.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4190119159088206,
"min": -1.0000000521540642,
"max": 1.4190119159088206,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 95.07379836589098,
"min": -31.998401656746864,
"max": 95.07379836589098,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4190119159088206,
"min": -1.0000000521540642,
"max": 1.4190119159088206,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 95.07379836589098,
"min": -31.998401656746864,
"max": 95.07379836589098,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.06933203956143541,
"min": 0.06933203956143541,
"max": 10.304304379038513,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.645246650616173,
"min": 4.299287130415905,
"max": 164.8688700646162,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1678273607",
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1.22.4",
"end_time_seconds": "1678275738"
},
"total": 2130.6041474559997,
"count": 1,
"self": 0.8001237429998582,
"children": {
"run_training.setup": {
"total": 0.1036977859999979,
"count": 1,
"self": 0.1036977859999979
},
"TrainerController.start_learning": {
"total": 2129.700325927,
"count": 1,
"self": 1.1496885539959294,
"children": {
"TrainerController._reset_env": {
"total": 6.128420777999963,
"count": 1,
"self": 6.128420777999963
},
"TrainerController.advance": {
"total": 2122.288210999004,
"count": 63286,
"self": 1.2992036169384846,
"children": {
"env_step": {
"total": 1395.433133355031,
"count": 63286,
"self": 1287.7827893421245,
"children": {
"SubprocessEnvManager._take_step": {
"total": 106.9166126729325,
"count": 63286,
"self": 4.519985165935054,
"children": {
"TorchPolicy.evaluate": {
"total": 102.39662750699745,
"count": 62546,
"self": 35.24273006301519,
"children": {
"TorchPolicy.sample_actions": {
"total": 67.15389744398226,
"count": 62546,
"self": 67.15389744398226
}
}
}
}
},
"workers": {
"total": 0.7337313399739287,
"count": 63286,
"self": 0.0,
"children": {
"worker_root": {
"total": 2125.5857099359478,
"count": 63286,
"is_parallel": true,
"self": 945.0116453969422,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019202920000225276,
"count": 1,
"is_parallel": true,
"self": 0.0006856840002456011,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012346079997769266,
"count": 8,
"is_parallel": true,
"self": 0.0012346079997769266
}
}
},
"UnityEnvironment.step": {
"total": 0.04617246099996919,
"count": 1,
"is_parallel": true,
"self": 0.0005235439998614311,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004518250000273838,
"count": 1,
"is_parallel": true,
"self": 0.0004518250000273838
},
"communicator.exchange": {
"total": 0.04356733300005544,
"count": 1,
"is_parallel": true,
"self": 0.04356733300005544
},
"steps_from_proto": {
"total": 0.001629759000024933,
"count": 1,
"is_parallel": true,
"self": 0.00042498100003740547,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012047779999875274,
"count": 8,
"is_parallel": true,
"self": 0.0012047779999875274
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1180.5740645390056,
"count": 63285,
"is_parallel": true,
"self": 30.1610956820291,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.38400288799164,
"count": 63285,
"is_parallel": true,
"self": 22.38400288799164
},
"communicator.exchange": {
"total": 1039.2893839969931,
"count": 63285,
"is_parallel": true,
"self": 1039.2893839969931
},
"steps_from_proto": {
"total": 88.73958197199181,
"count": 63285,
"is_parallel": true,
"self": 20.57024485189504,
"children": {
"_process_rank_one_or_two_observation": {
"total": 68.16933712009677,
"count": 506280,
"is_parallel": true,
"self": 68.16933712009677
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 725.5558740270345,
"count": 63286,
"self": 2.094590502043843,
"children": {
"process_trajectory": {
"total": 158.88835288398934,
"count": 63286,
"self": 158.657809839989,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23054304400034198,
"count": 2,
"self": 0.23054304400034198
}
}
},
"_update_policy": {
"total": 564.5729306410013,
"count": 428,
"self": 218.16442538401122,
"children": {
"TorchPPOOptimizer.update": {
"total": 346.4085052569901,
"count": 22830,
"self": 346.4085052569901
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2300001799303573e-06,
"count": 1,
"self": 1.2300001799303573e-06
},
"TrainerController._save_models": {
"total": 0.13400436599977184,
"count": 1,
"self": 0.002698247999887826,
"children": {
"RLTrainer._checkpoint": {
"total": 0.131306117999884,
"count": 1,
"self": 0.131306117999884
}
}
}
}
}
}
}