ppo-pyramids_1 / run_logs /timers.json
daripaez's picture
First training
51ab0c5
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.42536669969558716,
"min": 0.4174502491950989,
"max": 1.4487066268920898,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12590.8544921875,
"min": 12590.2998046875,
"max": 43947.96484375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989920.0,
"min": 29952.0,
"max": 989920.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989920.0,
"min": 29952.0,
"max": 989920.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.15278132259845734,
"min": -0.10743778944015503,
"max": 0.15278132259845734,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 37.73698806762695,
"min": -25.892507553100586,
"max": 37.73698806762695,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.14444099366664886,
"min": -0.14444099366664886,
"max": 0.18030865490436554,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -35.67692565917969,
"min": -35.67692565917969,
"max": 43.274078369140625,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06861378372984701,
"min": 0.06558704944709608,
"max": 0.07440885069843804,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0292067559477052,
"min": 0.4999584975293115,
"max": 1.0762430146540853,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.012752745410802567,
"min": 5.142104321752016e-05,
"max": 0.012752745410802567,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1912911811620385,
"min": 0.0006684735618277621,
"max": 0.1912911811620385,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.4285175238600004e-06,
"min": 7.4285175238600004e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011142776285790001,
"min": 0.00011142776285790001,
"max": 0.0033768388743871,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10247614000000001,
"min": 0.10247614000000001,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5371421,
"min": 1.3886848,
"max": 2.4256129000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025736638600000006,
"min": 0.00025736638600000006,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0038604957900000006,
"min": 0.0038604957900000006,
"max": 0.11257872870999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009170693345367908,
"min": 0.009108064696192741,
"max": 0.37443092465400696,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1375603973865509,
"min": 0.12751290202140808,
"max": 2.621016502380371,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 688.9268292682926,
"min": 688.9268292682926,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28246.0,
"min": 15984.0,
"max": 32903.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.5415237748197147,
"min": -1.0000000521540642,
"max": 0.6222571123923574,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 22.743998542428017,
"min": -30.995201602578163,
"max": 26.13479872047901,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.5415237748197147,
"min": -1.0000000521540642,
"max": 0.6222571123923574,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 22.743998542428017,
"min": -30.995201602578163,
"max": 26.13479872047901,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.06458955493733465,
"min": 0.06458955493733465,
"max": 7.991351058706641,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.712761307368055,
"min": 2.712761307368055,
"max": 127.86161693930626,
"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": "1674057139",
"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_1 --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": "1674058927"
},
"total": 1787.7383686030003,
"count": 1,
"self": 0.4905902810000953,
"children": {
"run_training.setup": {
"total": 0.11071673700007523,
"count": 1,
"self": 0.11071673700007523
},
"TrainerController.start_learning": {
"total": 1787.137061585,
"count": 1,
"self": 1.0706274220056002,
"children": {
"TrainerController._reset_env": {
"total": 5.954342868999902,
"count": 1,
"self": 5.954342868999902
},
"TrainerController.advance": {
"total": 1780.0282609919946,
"count": 63131,
"self": 1.104103498933,
"children": {
"env_step": {
"total": 1154.668960577077,
"count": 63131,
"self": 1057.5377258251801,
"children": {
"SubprocessEnvManager._take_step": {
"total": 96.44116463498585,
"count": 63131,
"self": 3.9493247120440174,
"children": {
"TorchPolicy.evaluate": {
"total": 92.49183992294184,
"count": 62551,
"self": 30.808679167912487,
"children": {
"TorchPolicy.sample_actions": {
"total": 61.68316075502935,
"count": 62551,
"self": 61.68316075502935
}
}
}
}
},
"workers": {
"total": 0.6900701169111016,
"count": 63131,
"self": 0.0,
"children": {
"worker_root": {
"total": 1784.0929751410836,
"count": 63131,
"is_parallel": true,
"self": 815.0578029670751,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001622009000129765,
"count": 1,
"is_parallel": true,
"self": 0.000569239000469679,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010527699996600859,
"count": 8,
"is_parallel": true,
"self": 0.0010527699996600859
}
}
},
"UnityEnvironment.step": {
"total": 0.04111463499975798,
"count": 1,
"is_parallel": true,
"self": 0.0004687109999395034,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040427300018563983,
"count": 1,
"is_parallel": true,
"self": 0.00040427300018563983
},
"communicator.exchange": {
"total": 0.03877939399990282,
"count": 1,
"is_parallel": true,
"self": 0.03877939399990282
},
"steps_from_proto": {
"total": 0.001462256999730016,
"count": 1,
"is_parallel": true,
"self": 0.0003650859998742817,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010971709998557344,
"count": 8,
"is_parallel": true,
"self": 0.0010971709998557344
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 969.0351721740085,
"count": 63130,
"is_parallel": true,
"self": 25.829545289975613,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 20.474871316914687,
"count": 63130,
"is_parallel": true,
"self": 20.474871316914687
},
"communicator.exchange": {
"total": 831.1887937570523,
"count": 63130,
"is_parallel": true,
"self": 831.1887937570523
},
"steps_from_proto": {
"total": 91.54196181006591,
"count": 63130,
"is_parallel": true,
"self": 19.78291812697671,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.7590436830892,
"count": 505040,
"is_parallel": true,
"self": 71.7590436830892
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 624.2551969159845,
"count": 63131,
"self": 1.9762277880909096,
"children": {
"process_trajectory": {
"total": 133.24336414288882,
"count": 63131,
"self": 132.70124936288948,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5421147799993378,
"count": 5,
"self": 0.5421147799993378
}
}
},
"_update_policy": {
"total": 489.03560498500474,
"count": 439,
"self": 182.73355974813785,
"children": {
"TorchPPOOptimizer.update": {
"total": 306.3020452368669,
"count": 22836,
"self": 306.3020452368669
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.810002327663824e-07,
"count": 1,
"self": 8.810002327663824e-07
},
"TrainerController._save_models": {
"total": 0.08382942099979118,
"count": 1,
"self": 0.0013700939989576,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08245932700083358,
"count": 1,
"self": 0.08245932700083358
}
}
}
}
}
}
}