ppo-Huggy / run_logs /timers.json
hugging-robot's picture
Huggy
aa6c016 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.408695936203003,
"min": 1.408695936203003,
"max": 1.42837655544281,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70143.1953125,
"min": 68582.6640625,
"max": 76626.5390625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 73.66268656716417,
"min": 73.66268656716417,
"max": 399.272,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49354.0,
"min": 49260.0,
"max": 50000.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999958.0,
"min": 49488.0,
"max": 1999958.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999958.0,
"min": 49488.0,
"max": 1999958.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4653120040893555,
"min": 0.03927173838019371,
"max": 2.5178322792053223,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1651.759033203125,
"min": 4.869695663452148,
"max": 1651.759033203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8380747919652,
"min": 1.7021851544418642,
"max": 3.9777810010803565,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2571.510110616684,
"min": 211.07095915079117,
"max": 2571.510110616684,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8380747919652,
"min": 1.7021851544418642,
"max": 3.9777810010803565,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2571.510110616684,
"min": 211.07095915079117,
"max": 2571.510110616684,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015473127237095874,
"min": 0.013156688333027786,
"max": 0.020269976863528428,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04641938171128762,
"min": 0.028599818328317875,
"max": 0.05715298273547281,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06690460873974693,
"min": 0.02289582459876935,
"max": 0.07049768225600322,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.2007138262192408,
"min": 0.0457916491975387,
"max": 0.2007138262192408,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7580987473333387e-06,
"min": 3.7580987473333387e-06,
"max": 0.000295330726556425,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1274296242000016e-05,
"min": 1.1274296242000016e-05,
"max": 0.0008441947686017499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1012526666666667,
"min": 0.1012526666666667,
"max": 0.19844357499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037580000000001,
"min": 0.20763675000000006,
"max": 0.5813982500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.250806666666678e-05,
"min": 7.250806666666678e-05,
"max": 0.0049223343925,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021752420000000034,
"min": 0.00021752420000000034,
"max": 0.014071772675000002,
"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": "1714888249",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714890639"
},
"total": 2390.355145981,
"count": 1,
"self": 0.4486394460000156,
"children": {
"run_training.setup": {
"total": 0.05935446000000866,
"count": 1,
"self": 0.05935446000000866
},
"TrainerController.start_learning": {
"total": 2389.847152075,
"count": 1,
"self": 4.2670594310257,
"children": {
"TrainerController._reset_env": {
"total": 3.0259061619999557,
"count": 1,
"self": 3.0259061619999557
},
"TrainerController.advance": {
"total": 2382.442279118974,
"count": 233338,
"self": 4.520806986991829,
"children": {
"env_step": {
"total": 1877.408422051066,
"count": 233338,
"self": 1555.7877924450634,
"children": {
"SubprocessEnvManager._take_step": {
"total": 318.82484859200235,
"count": 233338,
"self": 16.67322659403078,
"children": {
"TorchPolicy.evaluate": {
"total": 302.1516219979716,
"count": 222932,
"self": 302.1516219979716
}
}
},
"workers": {
"total": 2.7957810140003403,
"count": 233338,
"self": 0.0,
"children": {
"worker_root": {
"total": 2382.882421155985,
"count": 233338,
"is_parallel": true,
"self": 1123.0237417530172,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009007180000253356,
"count": 1,
"is_parallel": true,
"self": 0.00022727200001781966,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000673446000007516,
"count": 2,
"is_parallel": true,
"self": 0.000673446000007516
}
}
},
"UnityEnvironment.step": {
"total": 0.05407677200003036,
"count": 1,
"is_parallel": true,
"self": 0.00040082499998561616,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002211640000382431,
"count": 1,
"is_parallel": true,
"self": 0.0002211640000382431
},
"communicator.exchange": {
"total": 0.052701568000031784,
"count": 1,
"is_parallel": true,
"self": 0.052701568000031784
},
"steps_from_proto": {
"total": 0.0007532149999747162,
"count": 1,
"is_parallel": true,
"self": 0.0001916659999778858,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005615489999968304,
"count": 2,
"is_parallel": true,
"self": 0.0005615489999968304
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1259.8586794029677,
"count": 233337,
"is_parallel": true,
"self": 39.47164215995622,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.82996471902015,
"count": 233337,
"is_parallel": true,
"self": 83.82996471902015
},
"communicator.exchange": {
"total": 1045.6054162769367,
"count": 233337,
"is_parallel": true,
"self": 1045.6054162769367
},
"steps_from_proto": {
"total": 90.95165624705476,
"count": 233337,
"is_parallel": true,
"self": 32.970940760166854,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.9807154868879,
"count": 466674,
"is_parallel": true,
"self": 57.9807154868879
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 500.513050080916,
"count": 233338,
"self": 6.157283567963702,
"children": {
"process_trajectory": {
"total": 152.12296455495266,
"count": 233338,
"self": 150.6454835379527,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4774810169999455,
"count": 10,
"self": 1.4774810169999455
}
}
},
"_update_policy": {
"total": 342.23280195799964,
"count": 97,
"self": 278.43917909099866,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.79362286700098,
"count": 2910,
"self": 63.79362286700098
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.540000635548495e-07,
"count": 1,
"self": 8.540000635548495e-07
},
"TrainerController._save_models": {
"total": 0.11190650900016408,
"count": 1,
"self": 0.0018450030001986306,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11006150599996545,
"count": 1,
"self": 0.11006150599996545
}
}
}
}
}
}
}