ppo-Huggy / run_logs /timers.json
danielnbarbosa's picture
Huggy
a6dabcd verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4013803005218506,
"min": 1.4013803005218506,
"max": 1.4283115863800049,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70144.6875,
"min": 68714.796875,
"max": 77375.890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 82.395,
"min": 81.51320132013201,
"max": 408.0243902439024,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49437.0,
"min": 48894.0,
"max": 50187.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999921.0,
"min": 49855.0,
"max": 1999921.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999921.0,
"min": 49855.0,
"max": 1999921.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.422156572341919,
"min": 0.2165759652853012,
"max": 2.4746460914611816,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1453.2939453125,
"min": 26.42226791381836,
"max": 1469.4923095703125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8213252475857735,
"min": 1.8768255862056231,
"max": 4.009711371695442,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2292.795148551464,
"min": 228.97272151708603,
"max": 2300.9799332022667,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8213252475857735,
"min": 1.8768255862056231,
"max": 4.009711371695442,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2292.795148551464,
"min": 228.97272151708603,
"max": 2300.9799332022667,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015506387208390355,
"min": 0.011573441013266954,
"max": 0.021342661133773314,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.046519161625171064,
"min": 0.023146882026533908,
"max": 0.05841287360235583,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06003954514033264,
"min": 0.019269745300213498,
"max": 0.0608176385362943,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18011863542099793,
"min": 0.038539490600426995,
"max": 0.18011863542099793,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.328898890399998e-06,
"min": 3.328898890399998e-06,
"max": 0.00029534115155295,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.986696671199995e-06,
"min": 9.986696671199995e-06,
"max": 0.0008441395686201501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10110960000000002,
"min": 0.10110960000000002,
"max": 0.19844705,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30332880000000007,
"min": 0.2073899,
"max": 0.5813798499999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.536903999999998e-05,
"min": 6.536903999999998e-05,
"max": 0.004922507795000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019610711999999995,
"min": 0.00019610711999999995,
"max": 0.014070854515000002,
"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": "1741975172",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741977675"
},
"total": 2502.47145297,
"count": 1,
"self": 0.43858816700003445,
"children": {
"run_training.setup": {
"total": 0.02324938399988241,
"count": 1,
"self": 0.02324938399988241
},
"TrainerController.start_learning": {
"total": 2502.009615419,
"count": 1,
"self": 4.482549739917886,
"children": {
"TrainerController._reset_env": {
"total": 3.0447165299999597,
"count": 1,
"self": 3.0447165299999597
},
"TrainerController.advance": {
"total": 2494.3740652980828,
"count": 232680,
"self": 4.5901888572088865,
"children": {
"env_step": {
"total": 1995.520278612948,
"count": 232680,
"self": 1565.6199659480956,
"children": {
"SubprocessEnvManager._take_step": {
"total": 427.15341482390795,
"count": 232680,
"self": 15.871930166878656,
"children": {
"TorchPolicy.evaluate": {
"total": 411.2814846570293,
"count": 222955,
"self": 411.2814846570293
}
}
},
"workers": {
"total": 2.7468978409444844,
"count": 232680,
"self": 0.0,
"children": {
"worker_root": {
"total": 2494.191789590047,
"count": 232680,
"is_parallel": true,
"self": 1219.6771139411017,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010710560000006808,
"count": 1,
"is_parallel": true,
"self": 0.0004103349999695638,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000660721000031117,
"count": 2,
"is_parallel": true,
"self": 0.000660721000031117
}
}
},
"UnityEnvironment.step": {
"total": 0.02976844600016193,
"count": 1,
"is_parallel": true,
"self": 0.00032687600014469353,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024652900015098567,
"count": 1,
"is_parallel": true,
"self": 0.00024652900015098567
},
"communicator.exchange": {
"total": 0.028502975999799673,
"count": 1,
"is_parallel": true,
"self": 0.028502975999799673
},
"steps_from_proto": {
"total": 0.0006920650000665773,
"count": 1,
"is_parallel": true,
"self": 0.00022605099979955412,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004660140002670232,
"count": 2,
"is_parallel": true,
"self": 0.0004660140002670232
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1274.5146756489453,
"count": 232679,
"is_parallel": true,
"self": 37.78615085993283,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.8657490409937,
"count": 232679,
"is_parallel": true,
"self": 82.8657490409937
},
"communicator.exchange": {
"total": 1064.6700386759433,
"count": 232679,
"is_parallel": true,
"self": 1064.6700386759433
},
"steps_from_proto": {
"total": 89.19273707207549,
"count": 232679,
"is_parallel": true,
"self": 33.093189573025256,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.09954749905023,
"count": 465358,
"is_parallel": true,
"self": 56.09954749905023
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 494.2635978279259,
"count": 232680,
"self": 6.478127462816701,
"children": {
"process_trajectory": {
"total": 168.79240081210764,
"count": 232680,
"self": 167.47807448010758,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3143263320000642,
"count": 10,
"self": 1.3143263320000642
}
}
},
"_update_policy": {
"total": 318.99306955300153,
"count": 97,
"self": 254.57929912100326,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.41377043199827,
"count": 2910,
"self": 64.41377043199827
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.949996299634222e-07,
"count": 1,
"self": 8.949996299634222e-07
},
"TrainerController._save_models": {
"total": 0.10828295600003912,
"count": 1,
"self": 0.0018172159998357529,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10646574000020337,
"count": 1,
"self": 0.10646574000020337
}
}
}
}
}
}
}