ppo-huggy / run_logs /timers.json
rzimmerdev's picture
Huggy
98eaac4
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3973917961120605,
"min": 1.3973917961120605,
"max": 1.4244544506072998,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70494.2265625,
"min": 68282.6875,
"max": 77065.109375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 86.19304347826088,
"min": 85.37996545768567,
"max": 438.49122807017545,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49561.0,
"min": 49190.0,
"max": 49988.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999410.0,
"min": 49813.0,
"max": 1999410.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999410.0,
"min": 49813.0,
"max": 1999410.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.373750686645508,
"min": 0.01898745261132717,
"max": 2.445496082305908,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1364.9066162109375,
"min": 2.1455821990966797,
"max": 1369.689697265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.759292205105657,
"min": 1.8422204111002187,
"max": 3.963876647057293,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2161.593017935753,
"min": 208.17090645432472,
"max": 2203.915415763855,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.759292205105657,
"min": 1.8422204111002187,
"max": 3.963876647057293,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2161.593017935753,
"min": 208.17090645432472,
"max": 2203.915415763855,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01620983258746694,
"min": 0.012969334399591996,
"max": 0.019282722480905554,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04862949776240082,
"min": 0.02593866879918399,
"max": 0.05659443470552408,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.056163246639900744,
"min": 0.022703723516315222,
"max": 0.05844789780676365,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16848973991970223,
"min": 0.045407447032630444,
"max": 0.17534369342029094,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5443488185833384e-06,
"min": 3.5443488185833384e-06,
"max": 0.000295367926544025,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0633046455750015e-05,
"min": 1.0633046455750015e-05,
"max": 0.0008443059185647002,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118141666666665,
"min": 0.10118141666666665,
"max": 0.19845597499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30354424999999996,
"min": 0.20750115000000002,
"max": 0.5814353,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.895269166666674e-05,
"min": 6.895269166666674e-05,
"max": 0.0049229531524999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020685807500000025,
"min": 0.00020685807500000025,
"max": 0.014073621469999997,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1696696636",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1+cu118",
"numpy_version": "1.21.2",
"end_time_seconds": "1696699207"
},
"total": 2570.932649251,
"count": 1,
"self": 0.47916011200004505,
"children": {
"run_training.setup": {
"total": 0.07765041700000097,
"count": 1,
"self": 0.07765041700000097
},
"TrainerController.start_learning": {
"total": 2570.375838722,
"count": 1,
"self": 4.761218716988424,
"children": {
"TrainerController._reset_env": {
"total": 7.108138222000008,
"count": 1,
"self": 7.108138222000008
},
"TrainerController.advance": {
"total": 2558.4066908140117,
"count": 231735,
"self": 5.191682830976333,
"children": {
"env_step": {
"total": 1984.9622118850857,
"count": 231735,
"self": 1638.0107097181372,
"children": {
"SubprocessEnvManager._take_step": {
"total": 343.9610115319955,
"count": 231735,
"self": 17.280818462957882,
"children": {
"TorchPolicy.evaluate": {
"total": 326.6801930690376,
"count": 222876,
"self": 326.6801930690376
}
}
},
"workers": {
"total": 2.9904906349529483,
"count": 231735,
"self": 0.0,
"children": {
"worker_root": {
"total": 2562.8531308889246,
"count": 231735,
"is_parallel": true,
"self": 1234.955835098994,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007683949999943707,
"count": 1,
"is_parallel": true,
"self": 0.00023754000000053566,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000530854999993835,
"count": 2,
"is_parallel": true,
"self": 0.000530854999993835
}
}
},
"UnityEnvironment.step": {
"total": 0.03221042200001989,
"count": 1,
"is_parallel": true,
"self": 0.0003119319999882464,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002362150000010388,
"count": 1,
"is_parallel": true,
"self": 0.0002362150000010388
},
"communicator.exchange": {
"total": 0.026781228000004376,
"count": 1,
"is_parallel": true,
"self": 0.026781228000004376
},
"steps_from_proto": {
"total": 0.0048810470000262285,
"count": 1,
"is_parallel": true,
"self": 0.0002493679999986398,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004631679000027589,
"count": 2,
"is_parallel": true,
"self": 0.004631679000027589
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1327.8972957899307,
"count": 231734,
"is_parallel": true,
"self": 41.10126678679126,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.4762015870935,
"count": 231734,
"is_parallel": true,
"self": 88.4762015870935
},
"communicator.exchange": {
"total": 1096.4465645000228,
"count": 231734,
"is_parallel": true,
"self": 1096.4465645000228
},
"steps_from_proto": {
"total": 101.87326291602321,
"count": 231734,
"is_parallel": true,
"self": 39.63467399197026,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.23858892405295,
"count": 463468,
"is_parallel": true,
"self": 62.23858892405295
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 568.2527960979496,
"count": 231735,
"self": 6.882327323935328,
"children": {
"process_trajectory": {
"total": 156.4171691420129,
"count": 231735,
"self": 155.03623641101294,
"children": {
"RLTrainer._checkpoint": {
"total": 1.380932730999973,
"count": 10,
"self": 1.380932730999973
}
}
},
"_update_policy": {
"total": 404.9532996320014,
"count": 97,
"self": 342.86350885899293,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.089790773008474,
"count": 2910,
"self": 62.089790773008474
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0740000107034575e-06,
"count": 1,
"self": 1.0740000107034575e-06
},
"TrainerController._save_models": {
"total": 0.09978989499995805,
"count": 1,
"self": 0.0018227749997095088,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09796712000024854,
"count": 1,
"self": 0.09796712000024854
}
}
}
}
}
}
}