ppo-Huggy / run_logs /timers.json
lee-910530's picture
Huggy
31d12f0 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4074068069458008,
"min": 1.4073784351348877,
"max": 1.4281811714172363,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68550.5625,
"min": 68550.5625,
"max": 77140.2890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 113.30205949656751,
"min": 88.78918918918919,
"max": 379.7651515151515,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49513.0,
"min": 49014.0,
"max": 50129.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999936.0,
"min": 49932.0,
"max": 1999936.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999936.0,
"min": 49932.0,
"max": 1999936.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2944040298461914,
"min": 0.04522250220179558,
"max": 2.4074409008026123,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1002.6546020507812,
"min": 5.924147605895996,
"max": 1309.62255859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.448480455089761,
"min": 1.9055388369633042,
"max": 3.888491016404688,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1506.9859588742256,
"min": 249.62558764219284,
"max": 2074.1520067453384,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.448480455089761,
"min": 1.9055388369633042,
"max": 3.888491016404688,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1506.9859588742256,
"min": 249.62558764219284,
"max": 2074.1520067453384,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019927186955465005,
"min": 0.013277037199725329,
"max": 0.021247684985807307,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03985437391093001,
"min": 0.026554074399450657,
"max": 0.059175715229503115,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04579939345518748,
"min": 0.02427894625191887,
"max": 0.06242705711887942,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09159878691037496,
"min": 0.04855789250383774,
"max": 0.18728117135663827,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.659098446999995e-06,
"min": 4.659098446999995e-06,
"max": 0.00029528992657002493,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.31819689399999e-06,
"min": 9.31819689399999e-06,
"max": 0.0008439741186752999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.101553,
"min": 0.101553,
"max": 0.19842997499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.203106,
"min": 0.203106,
"max": 0.5813247000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.749469999999997e-05,
"min": 8.749469999999997e-05,
"max": 0.0049216557525,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017498939999999993,
"min": 0.00017498939999999993,
"max": 0.01406810253,
"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": "1744353535",
"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 --torch-device=cuda:0",
"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": "1744355959"
},
"total": 2424.512682625,
"count": 1,
"self": 0.7538029209999877,
"children": {
"run_training.setup": {
"total": 0.02347748700003649,
"count": 1,
"self": 0.02347748700003649
},
"TrainerController.start_learning": {
"total": 2423.735402217,
"count": 1,
"self": 4.353500588014867,
"children": {
"TrainerController._reset_env": {
"total": 3.028189019000024,
"count": 1,
"self": 3.028189019000024
},
"TrainerController.advance": {
"total": 2416.181490074985,
"count": 231568,
"self": 4.250963301939009,
"children": {
"env_step": {
"total": 1903.2378030839595,
"count": 231568,
"self": 1489.5724282390306,
"children": {
"SubprocessEnvManager._take_step": {
"total": 411.1737748909911,
"count": 231568,
"self": 15.469013124961066,
"children": {
"TorchPolicy.evaluate": {
"total": 395.70476176603006,
"count": 222974,
"self": 395.70476176603006
}
}
},
"workers": {
"total": 2.4915999539377367,
"count": 231568,
"self": 0.0,
"children": {
"worker_root": {
"total": 2416.153434574985,
"count": 231568,
"is_parallel": true,
"self": 1197.8902139659112,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010805080000295675,
"count": 1,
"is_parallel": true,
"self": 0.000269027000058486,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008114809999710815,
"count": 2,
"is_parallel": true,
"self": 0.0008114809999710815
}
}
},
"UnityEnvironment.step": {
"total": 0.028867728000022908,
"count": 1,
"is_parallel": true,
"self": 0.0003138020000506003,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020426700001507925,
"count": 1,
"is_parallel": true,
"self": 0.00020426700001507925
},
"communicator.exchange": {
"total": 0.027639113999953224,
"count": 1,
"is_parallel": true,
"self": 0.027639113999953224
},
"steps_from_proto": {
"total": 0.0007105450000040037,
"count": 1,
"is_parallel": true,
"self": 0.00018741799999588693,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005231270000081167,
"count": 2,
"is_parallel": true,
"self": 0.0005231270000081167
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1218.2632206090739,
"count": 231567,
"is_parallel": true,
"self": 36.72728969987793,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.97220153308928,
"count": 231567,
"is_parallel": true,
"self": 80.97220153308928
},
"communicator.exchange": {
"total": 1013.8876441109801,
"count": 231567,
"is_parallel": true,
"self": 1013.8876441109801
},
"steps_from_proto": {
"total": 86.67608526512674,
"count": 231567,
"is_parallel": true,
"self": 31.976365455164796,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.69971980996195,
"count": 463134,
"is_parallel": true,
"self": 54.69971980996195
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 508.6927236890865,
"count": 231568,
"self": 6.39763229202498,
"children": {
"process_trajectory": {
"total": 150.9650556380621,
"count": 231568,
"self": 149.62667727406262,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3383783639994817,
"count": 10,
"self": 1.3383783639994817
}
}
},
"_update_policy": {
"total": 351.33003575899943,
"count": 96,
"self": 283.2930655800021,
"children": {
"TorchPPOOptimizer.update": {
"total": 68.03697017899731,
"count": 2880,
"self": 68.03697017899731
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.264999809791334e-06,
"count": 1,
"self": 1.264999809791334e-06
},
"TrainerController._save_models": {
"total": 0.17222127000013643,
"count": 1,
"self": 0.0026431640003465873,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16957810599978984,
"count": 1,
"self": 0.16957810599978984
}
}
}
}
}
}
}