{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6666785478591919, "min": 0.5817809104919434, "max": 1.4159128665924072, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19989.689453125, "min": 17472.044921875, "max": 42953.1328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989878.0, "min": 29952.0, "max": 989878.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989878.0, "min": 29952.0, "max": 989878.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.13934296369552612, "min": -0.09717479348182678, "max": 0.24382330477237701, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 35.39311218261719, "min": -23.030426025390625, "max": 62.17494201660156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -4.381554126739502, "min": -4.9059624671936035, "max": 0.5944219827651978, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1112.914794921875, "min": -1236.302490234375, "max": 140.8780059814453, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07002881973555, "min": 0.06437616204217857, "max": 0.07260764432777209, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9804034762977001, "min": 0.48743108484456477, "max": 1.0608464345831297, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 4.384461223247594, "min": 0.00015916461683648984, "max": 5.405729892414523, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 61.38245712546631, "min": 0.002069140018874368, "max": 75.68021849380332, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.287440428028569e-06, "min": 7.287440428028569e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010202416599239997, "min": 0.00010202416599239997, "max": 0.0036300673899776, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242911428571431, "min": 0.10242911428571431, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340076000000004, "min": 1.3886848, "max": 2.6100223999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025266851714285713, "min": 0.00025266851714285713, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00353735924, "min": 0.00353735924, "max": 0.12102123776, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013929975219070911, "min": 0.013567755930125713, "max": 0.6271973848342896, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1950196474790573, "min": 0.18994858860969543, "max": 4.390381813049316, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 618.1276595744681, "min": 562.5833333333334, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29052.0, "min": 15984.0, "max": 33922.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.7904416370826463, "min": -1.0000000521540642, "max": 1.0610448672455184, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 37.94119857996702, "min": -28.949401542544365, "max": 51.9911984950304, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.7904416370826463, "min": -1.0000000521540642, "max": 1.0610448672455184, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 37.94119857996702, "min": -28.949401542544365, "max": 51.9911984950304, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09066129281867082, "min": 0.08976602471880235, "max": 13.936511846259236, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.351742055296199, "min": 4.231061337748542, "max": 222.98418954014778, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687646829", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1687649018" }, "total": 2188.708863598, "count": 1, "self": 0.47523825100006434, "children": { "run_training.setup": { "total": 0.03881868799999211, "count": 1, "self": 0.03881868799999211 }, "TrainerController.start_learning": { "total": 2188.194806659, "count": 1, "self": 1.4690428189992417, "children": { "TrainerController._reset_env": { "total": 4.070798954000111, "count": 1, "self": 4.070798954000111 }, "TrainerController.advance": { "total": 2182.5481425300004, "count": 63418, "self": 1.4860560470597193, "children": { "env_step": { "total": 1532.5697584049415, "count": 63418, "self": 1414.1254694899792, "children": { "SubprocessEnvManager._take_step": { "total": 117.57364631492169, "count": 63418, "self": 5.210092892968532, "children": { "TorchPolicy.evaluate": { "total": 112.36355342195316, "count": 62576, "self": 112.36355342195316 } } }, "workers": { "total": 0.8706426000405827, "count": 63418, "self": 0.0, "children": { "worker_root": { "total": 2183.1519527290034, "count": 63418, "is_parallel": true, "self": 889.2825318490243, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0035303209999710816, "count": 1, "is_parallel": true, "self": 0.0009593449999556469, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025709760000154347, "count": 8, "is_parallel": true, "self": 0.0025709760000154347 } } }, "UnityEnvironment.step": { "total": 0.051048893999904976, "count": 1, "is_parallel": true, "self": 0.0005976359998385306, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005891739999697165, "count": 1, "is_parallel": true, "self": 0.0005891739999697165 }, "communicator.exchange": { "total": 0.04797203399994032, "count": 1, "is_parallel": true, "self": 0.04797203399994032 }, "steps_from_proto": { "total": 0.001890050000156407, "count": 1, "is_parallel": true, "self": 0.0003690099997584184, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015210400003979885, "count": 8, "is_parallel": true, "self": 0.0015210400003979885 } } } } } } }, "UnityEnvironment.step": { "total": 1293.869420879979, "count": 63417, "is_parallel": true, "self": 34.26095651600872, "children": { "UnityEnvironment._generate_step_input": { "total": 24.930329854004185, "count": 63417, "is_parallel": true, "self": 24.930329854004185 }, "communicator.exchange": { "total": 1124.8860778850092, "count": 63417, "is_parallel": true, "self": 1124.8860778850092 }, "steps_from_proto": { "total": 109.79205662495701, "count": 63417, "is_parallel": true, "self": 21.849666424004226, "children": { "_process_rank_one_or_two_observation": { "total": 87.94239020095279, "count": 507336, "is_parallel": true, "self": 87.94239020095279 } } } } } } } } } } }, "trainer_advance": { "total": 648.4923280779994, "count": 63418, "self": 2.767289411971433, "children": { "process_trajectory": { "total": 116.5806324690243, "count": 63418, "self": 116.3665984980239, "children": { "RLTrainer._checkpoint": { "total": 0.21403397100039, "count": 2, "self": 0.21403397100039 } } }, "_update_policy": { "total": 529.1444061970037, "count": 455, "self": 339.3747685630292, "children": { "TorchPPOOptimizer.update": { "total": 189.76963763397453, "count": 22803, "self": 189.76963763397453 } } } } } } }, "trainer_threads": { "total": 1.0320000001229346e-06, "count": 1, "self": 1.0320000001229346e-06 }, "TrainerController._save_models": { "total": 0.10682132400006594, "count": 1, "self": 0.0014866120004626282, "children": { "RLTrainer._checkpoint": { "total": 0.10533471199960331, "count": 1, "self": 0.10533471199960331 } } } } } } }