ppo-Pyramids / run_logs /timers.json
emmashe15's picture
First Push
58bc844
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.14292973279953003,
"min": 0.11940550804138184,
"max": 1.4193896055221558,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 4287.89208984375,
"min": 3571.55322265625,
"max": 43058.6015625,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999956.0,
"min": 29952.0,
"max": 2999956.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999956.0,
"min": 29952.0,
"max": 2999956.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7337890267372131,
"min": -0.0974569022655487,
"max": 0.8745170831680298,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 218.66912841796875,
"min": -23.38965606689453,
"max": 267.60223388671875,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.00890808179974556,
"min": 0.005811864510178566,
"max": 0.35619595646858215,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.6546082496643066,
"min": 1.6854406595230103,
"max": 84.41844177246094,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06833154014635107,
"min": 0.06399497415978692,
"max": 0.07514426053461587,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.024973102195266,
"min": 0.4874997344426677,
"max": 1.0692854776017495,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.017900132499764573,
"min": 0.00010899150240232841,
"max": 0.017900132499764573,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2685019874964686,
"min": 0.0010899150240232841,
"max": 0.2685019874964686,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.493559502180004e-06,
"min": 1.493559502180004e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.2403392532700062e-05,
"min": 2.2403392532700062e-05,
"max": 0.0037593076468974995,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10049782,
"min": 0.10049782,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5074673,
"min": 1.3897045333333333,
"max": 2.7375006,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 5.973221800000014e-05,
"min": 5.973221800000014e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008959832700000021,
"min": 0.0008959832700000021,
"max": 0.12532493975,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010917965322732925,
"min": 0.010454429313540459,
"max": 0.412590354681015,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.16376948356628418,
"min": 0.14636200666427612,
"max": 2.8881325721740723,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 239.45454545454547,
"min": 200.07333333333332,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31608.0,
"min": 15984.0,
"max": 32626.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6677419668390552,
"min": -1.0000000521540642,
"max": 1.8003873107298998,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 218.4741976559162,
"min": -32.000001668930054,
"max": 269.9889975488186,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6677419668390552,
"min": -1.0000000521540642,
"max": 1.8003873107298998,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 218.4741976559162,
"min": -32.000001668930054,
"max": 269.9889975488186,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.027038944790824956,
"min": 0.022283377670889972,
"max": 7.986746062524617,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.5421017675980693,
"min": 3.1401077657646965,
"max": 127.78793700039387,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1673618390",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1.21.6",
"end_time_seconds": "1673625632"
},
"total": 7242.3605654210005,
"count": 1,
"self": 0.4372184270014259,
"children": {
"run_training.setup": {
"total": 0.105973203999838,
"count": 1,
"self": 0.105973203999838
},
"TrainerController.start_learning": {
"total": 7241.81737379,
"count": 1,
"self": 4.579230756133256,
"children": {
"TrainerController._reset_env": {
"total": 6.543547028000148,
"count": 1,
"self": 6.543547028000148
},
"TrainerController.advance": {
"total": 7230.586427100864,
"count": 195016,
"self": 4.490833558803388,
"children": {
"env_step": {
"total": 5159.303983696915,
"count": 195016,
"self": 4810.334707433127,
"children": {
"SubprocessEnvManager._take_step": {
"total": 346.29557439382916,
"count": 195016,
"self": 13.882790613081852,
"children": {
"TorchPolicy.evaluate": {
"total": 332.4127837807473,
"count": 187550,
"self": 111.8615250430737,
"children": {
"TorchPolicy.sample_actions": {
"total": 220.5512587376736,
"count": 187550,
"self": 220.5512587376736
}
}
}
}
},
"workers": {
"total": 2.6737018699591317,
"count": 195016,
"self": 0.0,
"children": {
"worker_root": {
"total": 7226.187007238168,
"count": 195016,
"is_parallel": true,
"self": 2751.6561048512895,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020136030000230676,
"count": 1,
"is_parallel": true,
"self": 0.0007262540002557216,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001287348999767346,
"count": 8,
"is_parallel": true,
"self": 0.001287348999767346
}
}
},
"UnityEnvironment.step": {
"total": 0.05069685099988419,
"count": 1,
"is_parallel": true,
"self": 0.0005426359998637054,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005443689999538037,
"count": 1,
"is_parallel": true,
"self": 0.0005443689999538037
},
"communicator.exchange": {
"total": 0.04759826800000155,
"count": 1,
"is_parallel": true,
"self": 0.04759826800000155
},
"steps_from_proto": {
"total": 0.0020115780000651284,
"count": 1,
"is_parallel": true,
"self": 0.0005427880003026075,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001468789999762521,
"count": 8,
"is_parallel": true,
"self": 0.001468789999762521
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 4474.530902386879,
"count": 195015,
"is_parallel": true,
"self": 91.20027822259453,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 75.49031692596441,
"count": 195015,
"is_parallel": true,
"self": 75.49031692596441
},
"communicator.exchange": {
"total": 3963.4243047810323,
"count": 195015,
"is_parallel": true,
"self": 3963.4243047810323
},
"steps_from_proto": {
"total": 344.4160024572873,
"count": 195015,
"is_parallel": true,
"self": 76.94733183536914,
"children": {
"_process_rank_one_or_two_observation": {
"total": 267.46867062191814,
"count": 1560120,
"is_parallel": true,
"self": 267.46867062191814
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2066.7916098451456,
"count": 195016,
"self": 8.21757212244438,
"children": {
"process_trajectory": {
"total": 481.03133866070357,
"count": 195016,
"self": 480.4249248987021,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6064137620014662,
"count": 6,
"self": 0.6064137620014662
}
}
},
"_update_policy": {
"total": 1577.5426990619974,
"count": 1378,
"self": 598.4271979679559,
"children": {
"TorchPPOOptimizer.update": {
"total": 979.1155010940415,
"count": 68439,
"self": 979.1155010940415
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.470015018247068e-07,
"count": 1,
"self": 8.470015018247068e-07
},
"TrainerController._save_models": {
"total": 0.10816805800095608,
"count": 1,
"self": 0.0015202980011963518,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10664775999975973,
"count": 1,
"self": 0.10664775999975973
}
}
}
}
}
}
}