Hanna Tochylina
First Push
73edf77
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.392561674118042,
"min": 1.3791170120239258,
"max": 2.8755123615264893,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 13326.8154296875,
"min": 13326.8154296875,
"max": 29511.3828125,
"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": 10.53276538848877,
"min": 0.2741548717021942,
"max": 10.53276538848877,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2053.88916015625,
"min": 53.18604278564453,
"max": 2091.6982421875,
"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": 0.033600884725577394,
"min": 0.022576354922572744,
"max": 0.034714985387593815,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.13440353890230958,
"min": 0.09030541969029098,
"max": 0.17357492693796908,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.26236972274879616,
"min": 0.14036813642208773,
"max": 0.32896537333726883,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.0494788909951847,
"min": 0.5614725456883509,
"max": 1.6101494878530502,
"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": 0.0013851600382799997,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.102694,
"min": 0.102694,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.410776,
"min": 0.410776,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014443060000000012,
"min": 0.00014443060000000012,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000005,
"min": 0.0005777224000000005,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 20.795454545454547,
"min": 3.25,
"max": 20.795454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 915.0,
"min": 143.0,
"max": 1124.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 20.795454545454547,
"min": 3.25,
"max": 20.795454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 915.0,
"min": 143.0,
"max": 1124.0,
"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": "1680611510",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget5 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.10.1+cu111",
"numpy_version": "1.21.2",
"end_time_seconds": "1680612070"
},
"total": 559.2142530830001,
"count": 1,
"self": 0.8112668400003713,
"children": {
"run_training.setup": {
"total": 0.06610792499986928,
"count": 1,
"self": 0.06610792499986928
},
"TrainerController.start_learning": {
"total": 558.3368783179999,
"count": 1,
"self": 0.7555025509677762,
"children": {
"TrainerController._reset_env": {
"total": 8.012764305000019,
"count": 1,
"self": 8.012764305000019
},
"TrainerController.advance": {
"total": 549.3495609690322,
"count": 18207,
"self": 0.4478565750087,
"children": {
"env_step": {
"total": 548.9017043940235,
"count": 18207,
"self": 378.156553840015,
"children": {
"SubprocessEnvManager._take_step": {
"total": 170.35278862303312,
"count": 18207,
"self": 2.2840592599886804,
"children": {
"TorchPolicy.evaluate": {
"total": 168.06872936304444,
"count": 18207,
"self": 168.06872936304444
}
}
},
"workers": {
"total": 0.39236193097531213,
"count": 18207,
"self": 0.0,
"children": {
"worker_root": {
"total": 556.0335656449797,
"count": 18207,
"is_parallel": true,
"self": 247.06433609696842,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003184785000030388,
"count": 1,
"is_parallel": true,
"self": 0.0009529169992674724,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022318680007629155,
"count": 10,
"is_parallel": true,
"self": 0.0022318680007629155
}
}
},
"UnityEnvironment.step": {
"total": 0.03934724800001277,
"count": 1,
"is_parallel": true,
"self": 0.0006229709997569444,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00033577800013517844,
"count": 1,
"is_parallel": true,
"self": 0.00033577800013517844
},
"communicator.exchange": {
"total": 0.03636464100009107,
"count": 1,
"is_parallel": true,
"self": 0.03636464100009107
},
"steps_from_proto": {
"total": 0.002023858000029577,
"count": 1,
"is_parallel": true,
"self": 0.0004057019996253075,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016181560004042694,
"count": 10,
"is_parallel": true,
"self": 0.0016181560004042694
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 308.9692295480113,
"count": 18206,
"is_parallel": true,
"self": 11.70244125999261,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.311300536006911,
"count": 18206,
"is_parallel": true,
"self": 6.311300536006911
},
"communicator.exchange": {
"total": 251.2451653109788,
"count": 18206,
"is_parallel": true,
"self": 251.2451653109788
},
"steps_from_proto": {
"total": 39.710322441032986,
"count": 18206,
"is_parallel": true,
"self": 8.463814690946037,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.24650775008695,
"count": 182060,
"is_parallel": true,
"self": 31.24650775008695
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012018500001431676,
"count": 1,
"self": 0.00012018500001431676,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 543.2585216660996,
"count": 648132,
"is_parallel": true,
"self": 17.75974138108313,
"children": {
"process_trajectory": {
"total": 366.67751295301605,
"count": 648132,
"is_parallel": true,
"self": 365.2147660940159,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4627468590001627,
"count": 4,
"is_parallel": true,
"self": 1.4627468590001627
}
}
},
"_update_policy": {
"total": 158.8212673320004,
"count": 90,
"is_parallel": true,
"self": 96.06748758400317,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.753779747997214,
"count": 1080,
"is_parallel": true,
"self": 62.753779747997214
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2189303079999263,
"count": 1,
"self": 0.0013074769999548153,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21762283099997148,
"count": 1,
"self": 0.21762283099997148
}
}
}
}
}
}
}