ppo-Huggy / run_logs /timers.json
davidfarah's picture
Huggy
2a9ff61 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3272204399108887,
"min": 1.3271385431289673,
"max": 1.4058014154434204,
"count": 160
},
"Huggy.Policy.Entropy.sum": {
"value": 67016.671875,
"min": 63891.125,
"max": 71432.984375,
"count": 160
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 438.219298245614,
"min": 64.32591623036649,
"max": 449.6936936936937,
"count": 160
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49957.0,
"min": 48647.0,
"max": 50435.0,
"count": 160
},
"Huggy.Step.mean": {
"value": 9999737.0,
"min": 2049968.0,
"max": 9999737.0,
"count": 160
},
"Huggy.Step.sum": {
"value": 9999737.0,
"min": 2049968.0,
"max": 9999737.0,
"count": 160
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 1.2435041666030884,
"min": 1.1603810787200928,
"max": 2.6198484897613525,
"count": 160
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 141.7594757080078,
"min": 129.98377990722656,
"max": 1928.8643798828125,
"count": 160
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 1.8722117671808391,
"min": 1.6747096312853198,
"max": 4.023067058303079,
"count": 160
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 213.43214145861566,
"min": 195.9410268603824,
"max": 3002.07651001215,
"count": 160
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 1.8722117671808391,
"min": 1.6747096312853198,
"max": 4.023067058303079,
"count": 160
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 213.43214145861566,
"min": 195.9410268603824,
"max": 3002.07651001215,
"count": 160
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01756259978024496,
"min": 0.012297437878441998,
"max": 0.02109607246845068,
"count": 160
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05268779934073488,
"min": 0.024594875756883995,
"max": 0.05882402316977581,
"count": 160
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.005349170592510038,
"min": 0.0034958512910331285,
"max": 0.07474070060998202,
"count": 160
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.016047511777530114,
"min": 0.006991702582066257,
"max": 0.2137989319860935,
"count": 160
},
"Huggy.Policy.LearningRate.mean": {
"value": 6.541497819833391e-07,
"min": 6.541497819833391e-07,
"max": 0.00023907573530809495,
"count": 160
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.9624493459500175e-06,
"min": 1.9624493459500175e-06,
"max": 0.0007089171936942901,
"count": 160
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10021801666666669,
"min": 0.10021801666666669,
"max": 0.17969190499999999,
"count": 160
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30065405000000006,
"min": 0.20146836000000007,
"max": 0.5363057099999999,
"count": 160
},
"Huggy.Policy.Beta.mean": {
"value": 2.0879031666666767e-05,
"min": 2.0879031666666767e-05,
"max": 0.0039866260595000005,
"count": 160
},
"Huggy.Policy.Beta.sum": {
"value": 6.26370950000003e-05,
"min": 6.26370950000003e-05,
"max": 0.011821654929000001,
"count": 160
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 160
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 160
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1720011719",
"python_version": "3.10.10 (main, Mar 21 2023, 18:45:11) [GCC 11.2.0]",
"command_line_arguments": "/home/david/miniconda3/envs/rltut/bin/mlagents-learn ./ml-agents/config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --resume --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1720014500"
},
"total": 2781.18679205,
"count": 1,
"self": 0.16616158400120185,
"children": {
"run_training.setup": {
"total": 0.014461128999755601,
"count": 1,
"self": 0.014461128999755601
},
"TrainerController.start_learning": {
"total": 2781.006169336999,
"count": 1,
"self": 7.133989096978439,
"children": {
"TrainerController._reset_env": {
"total": 0.5893602159994771,
"count": 1,
"self": 0.5893602159994771
},
"TrainerController.advance": {
"total": 2773.2422049390198,
"count": 927449,
"self": 6.8164848244559835,
"children": {
"env_step": {
"total": 2158.021989628317,
"count": 927449,
"self": 1670.9593255387645,
"children": {
"SubprocessEnvManager._take_step": {
"total": 482.33436187742063,
"count": 927449,
"self": 25.79233400634439,
"children": {
"TorchPolicy.evaluate": {
"total": 456.54202787107624,
"count": 891616,
"self": 456.54202787107624
}
}
},
"workers": {
"total": 4.728302212131894,
"count": 927449,
"self": 0.0,
"children": {
"worker_root": {
"total": 2772.9763229670725,
"count": 927449,
"is_parallel": true,
"self": 1459.821563829878,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00039839100008975947,
"count": 1,
"is_parallel": true,
"self": 0.00011836499925266253,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00028002600083709694,
"count": 2,
"is_parallel": true,
"self": 0.00028002600083709694
}
}
},
"UnityEnvironment.step": {
"total": 0.008414907999394927,
"count": 1,
"is_parallel": true,
"self": 9.762600075191585e-05,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 9.688599948276533e-05,
"count": 1,
"is_parallel": true,
"self": 9.688599948276533e-05
},
"communicator.exchange": {
"total": 0.007950434999656864,
"count": 1,
"is_parallel": true,
"self": 0.007950434999656864
},
"steps_from_proto": {
"total": 0.0002699609995033825,
"count": 1,
"is_parallel": true,
"self": 8.456599971395917e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0001853949997894233,
"count": 2,
"is_parallel": true,
"self": 0.0001853949997894233
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1313.1547591371946,
"count": 927448,
"is_parallel": true,
"self": 39.488415066145535,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 72.13615247579855,
"count": 927448,
"is_parallel": true,
"self": 72.13615247579855
},
"communicator.exchange": {
"total": 1112.2906034919288,
"count": 927448,
"is_parallel": true,
"self": 1112.2906034919288
},
"steps_from_proto": {
"total": 89.2395881033217,
"count": 927448,
"is_parallel": true,
"self": 30.434471904509337,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.80511619881236,
"count": 1854896,
"is_parallel": true,
"self": 58.80511619881236
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 608.4037304862468,
"count": 927449,
"self": 10.315836025705721,
"children": {
"process_trajectory": {
"total": 208.5888295145396,
"count": 927449,
"self": 207.0362994825373,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5525300320023234,
"count": 40,
"self": 1.5525300320023234
}
}
},
"_update_policy": {
"total": 389.49906494600145,
"count": 387,
"self": 322.8278014800535,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.67126346594796,
"count": 11610,
"self": 66.67126346594796
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.1600105760153383e-07,
"count": 1,
"self": 4.1600105760153383e-07
},
"TrainerController._save_models": {
"total": 0.04061466900020605,
"count": 1,
"self": 0.00123130899919488,
"children": {
"RLTrainer._checkpoint": {
"total": 0.03938336000101117,
"count": 1,
"self": 0.03938336000101117
}
}
}
}
}
}
}