{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0766135454177856, "min": 1.0766135454177856, "max": 2.8732972145080566, "count": 15 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11084.8134765625, "min": 10622.7578125, "max": 29425.4375, "count": 15 }, "SnowballTarget.Step.mean": { "value": 149984.0, "min": 9952.0, "max": 149984.0, "count": 15 }, "SnowballTarget.Step.sum": { "value": 149984.0, "min": 9952.0, "max": 149984.0, "count": 15 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.062546730041504, "min": 0.29374516010284424, "max": 12.062546730041504, "count": 15 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2472.822021484375, "min": 56.9865608215332, "max": 2472.822021484375, "count": 15 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 15 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 15 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0664566765392117, "min": 0.0634678657548184, "max": 0.07378272737513922, "count": 15 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3322833826960585, "min": 0.2538714630192736, "max": 0.36891363687569606, "count": 15 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24117048277574424, "min": 0.10578430249405951, "max": 0.2924988298293422, "count": 15 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.2058524138787212, "min": 0.42313720997623805, "max": 1.4092775396272248, "count": 15 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 9.776096741333334e-06, "min": 9.776096741333334e-06, "max": 0.000289176003608, "count": 15 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 4.888048370666667e-05, "min": 4.888048370666667e-05, "max": 0.0013468800510399999, "count": 15 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10325866666666668, "min": 0.10325866666666668, "max": 0.19639199999999998, "count": 15 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5162933333333334, "min": 0.43943466666666664, "max": 0.94896, "count": 15 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00017260746666666673, "min": 0.00017260746666666673, "max": 0.004819960799999999, "count": 15 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0008630373333333337, "min": 0.0008630373333333337, "max": 0.022453104, "count": 15 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 23.89090909090909, "min": 3.272727272727273, "max": 24.08888888888889, "count": 15 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1314.0, "min": 144.0, "max": 1320.0, "count": 15 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.89090909090909, "min": 3.272727272727273, "max": 24.08888888888889, "count": 15 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1314.0, "min": 144.0, "max": 1320.0, "count": 15 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 15 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 15 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679197674", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1679198025" }, "total": 350.558789015, "count": 1, "self": 0.6439106060001905, "children": { "run_training.setup": { "total": 0.10663518599994859, "count": 1, "self": 0.10663518599994859 }, "TrainerController.start_learning": { "total": 349.80824322299986, "count": 1, "self": 0.45925794699473954, "children": { "TrainerController._reset_env": { "total": 8.726951916999951, "count": 1, "self": 8.726951916999951 }, "TrainerController.advance": { "total": 340.42245681300506, "count": 13673, "self": 0.22369988300727073, "children": { "env_step": { "total": 340.1987569299978, "count": 13673, "self": 243.2639873499943, "children": { "SubprocessEnvManager._take_step": { "total": 96.715374949992, "count": 13673, "self": 1.6801264899977468, "children": { "TorchPolicy.evaluate": { "total": 95.03524845999425, "count": 13673, "self": 95.03524845999425 } } }, "workers": { "total": 0.21939463001149306, "count": 13673, "self": 0.0, "children": { "worker_root": { "total": 348.68469877001166, "count": 13673, "is_parallel": true, "self": 166.06826669501197, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005490742999995746, "count": 1, "is_parallel": true, "self": 0.004041198999743756, "children": { "_process_rank_one_or_two_observation": { "total": 0.00144954400025199, "count": 10, "is_parallel": true, "self": 0.00144954400025199 } } }, "UnityEnvironment.step": { "total": 0.04917816500005756, "count": 1, "is_parallel": true, "self": 0.0005532529999072722, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003999190000740782, "count": 1, "is_parallel": true, "self": 0.0003999190000740782 }, "communicator.exchange": { "total": 0.046454961999984334, "count": 1, "is_parallel": true, "self": 0.046454961999984334 }, "steps_from_proto": { "total": 0.0017700310000918762, "count": 1, "is_parallel": true, "self": 0.0003787710001006417, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013912599999912345, "count": 10, "is_parallel": true, "self": 0.0013912599999912345 } } } } } } }, "UnityEnvironment.step": { "total": 182.6164320749997, "count": 13672, "is_parallel": true, "self": 7.206349867002018, "children": { "UnityEnvironment._generate_step_input": { "total": 3.8256777529967394, "count": 13672, "is_parallel": true, "self": 3.8256777529967394 }, "communicator.exchange": { "total": 148.31455275799965, "count": 13672, "is_parallel": true, "self": 148.31455275799965 }, "steps_from_proto": { "total": 23.269851697001286, "count": 13672, "is_parallel": true, "self": 4.734702763000314, "children": { "_process_rank_one_or_two_observation": { "total": 18.535148934000972, "count": 136720, "is_parallel": true, "self": 18.535148934000972 } } } } } } } } } } } } }, "trainer_threads": { "total": 9.439700011171226e-05, "count": 1, "self": 9.439700011171226e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 337.842844157021, "count": 308926, "is_parallel": true, "self": 7.579419459010637, "children": { "process_trajectory": { "total": 188.76615222700968, "count": 308926, "is_parallel": true, "self": 188.09915663500965, "children": { "RLTrainer._checkpoint": { "total": 0.6669955920000348, "count": 3, "is_parallel": true, "self": 0.6669955920000348 } } }, "_update_policy": { "total": 141.49727247100066, "count": 68, "is_parallel": true, "self": 50.49787374600248, "children": { "TorchPPOOptimizer.update": { "total": 90.99939872499817, "count": 3465, "is_parallel": true, "self": 90.99939872499817 } } } } } } } } }, "TrainerController._save_models": { "total": 0.19948214900000494, "count": 1, "self": 0.0011462299999038805, "children": { "RLTrainer._checkpoint": { "total": 0.19833591900010106, "count": 1, "self": 0.19833591900010106 } } } } } } }