pnm's picture
First Push
39f167c
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8089434504508972,
"min": 0.7647393345832825,
"max": 2.8713600635528564,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7723.7919921875,
"min": 7723.7919921875,
"max": 29405.599609375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.34854507446289,
"min": 0.295878529548645,
"max": 12.34854507446289,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2407.96630859375,
"min": 57.40043258666992,
"max": 2463.369140625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06344445263811413,
"min": 0.06323007691478102,
"max": 0.07482843066362536,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2537778105524565,
"min": 0.2537521960073397,
"max": 0.37414215331812684,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19658531241264998,
"min": 0.10525086732106465,
"max": 0.28784075408589604,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7863412496505999,
"min": 0.4210034692842586,
"max": 1.4392037704294802,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.113636363636363,
"min": 2.75,
"max": 25.113636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1105.0,
"min": 121.0,
"max": 1325.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.113636363636363,
"min": 2.75,
"max": 25.113636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1105.0,
"min": 121.0,
"max": 1325.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1699500940",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1699501411"
},
"total": 470.95280016999993,
"count": 1,
"self": 0.4390218339998455,
"children": {
"run_training.setup": {
"total": 0.04756368400001065,
"count": 1,
"self": 0.04756368400001065
},
"TrainerController.start_learning": {
"total": 470.4662146520001,
"count": 1,
"self": 0.5272588060021235,
"children": {
"TrainerController._reset_env": {
"total": 9.870370576999903,
"count": 1,
"self": 9.870370576999903
},
"TrainerController.advance": {
"total": 459.98206089899804,
"count": 18199,
"self": 0.2732826830083468,
"children": {
"env_step": {
"total": 459.7087782159897,
"count": 18199,
"self": 315.01881596499254,
"children": {
"SubprocessEnvManager._take_step": {
"total": 144.4145335339923,
"count": 18199,
"self": 1.398605782993286,
"children": {
"TorchPolicy.evaluate": {
"total": 143.01592775099903,
"count": 18199,
"self": 143.01592775099903
}
}
},
"workers": {
"total": 0.27542871700484284,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 469.2020690439998,
"count": 18199,
"is_parallel": true,
"self": 228.7709726929818,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006148355999926025,
"count": 1,
"is_parallel": true,
"self": 0.004745866999769532,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014024890001564927,
"count": 10,
"is_parallel": true,
"self": 0.0014024890001564927
}
}
},
"UnityEnvironment.step": {
"total": 0.0468176179999773,
"count": 1,
"is_parallel": true,
"self": 0.0006329969999114837,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003871490000619815,
"count": 1,
"is_parallel": true,
"self": 0.0003871490000619815
},
"communicator.exchange": {
"total": 0.043798300000048584,
"count": 1,
"is_parallel": true,
"self": 0.043798300000048584
},
"steps_from_proto": {
"total": 0.0019991719999552515,
"count": 1,
"is_parallel": true,
"self": 0.0003743259995871995,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001624846000368052,
"count": 10,
"is_parallel": true,
"self": 0.001624846000368052
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 240.43109635101803,
"count": 18198,
"is_parallel": true,
"self": 10.674001197989014,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3376249110210665,
"count": 18198,
"is_parallel": true,
"self": 5.3376249110210665
},
"communicator.exchange": {
"total": 190.53073964399846,
"count": 18198,
"is_parallel": true,
"self": 190.53073964399846
},
"steps_from_proto": {
"total": 33.88873059800949,
"count": 18198,
"is_parallel": true,
"self": 6.2991492850105715,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.589581312998916,
"count": 181980,
"is_parallel": true,
"self": 27.589581312998916
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.9864999962446745e-05,
"count": 1,
"self": 3.9864999962446745e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 456.2421634710255,
"count": 472968,
"is_parallel": true,
"self": 9.979865870012759,
"children": {
"process_trajectory": {
"total": 256.6419417400126,
"count": 472968,
"is_parallel": true,
"self": 255.91293989501253,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7290018450000844,
"count": 4,
"is_parallel": true,
"self": 0.7290018450000844
}
}
},
"_update_policy": {
"total": 189.62035586100012,
"count": 90,
"is_parallel": true,
"self": 58.81437621000509,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.80597965099503,
"count": 4584,
"is_parallel": true,
"self": 130.80597965099503
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08648450500004401,
"count": 1,
"self": 0.00089726300006987,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08558724199997414,
"count": 1,
"self": 0.08558724199997414
}
}
}
}
}
}
}