{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4799734055995941, "min": 0.4799734055995941, "max": 1.4420990943908691, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14591.19140625, "min": 14514.9072265625, "max": 43747.51953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989915.0, "min": 29993.0, "max": 989915.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989915.0, "min": 29993.0, "max": 989915.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3836113512516022, "min": -0.11039615422487259, "max": 0.4589192271232605, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 105.49311828613281, "min": -26.605472564697266, "max": 122.53143310546875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01889864169061184, "min": -0.004501071758568287, "max": 0.36127710342407227, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.197126388549805, "min": -1.192784070968628, "max": 85.98394775390625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07103444427613996, "min": 0.06572987610624631, "max": 0.07216869629353061, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0655166641420994, "min": 0.5660138436391033, "max": 1.0737435170449317, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01635689329009943, "min": 0.000503590415832798, "max": 0.01635689329009943, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24535339935149145, "min": 0.006546675405826375, "max": 0.24535339935149145, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.485537504853332e-06, "min": 7.485537504853332e-06, "max": 0.00029484978921673756, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011228306257279998, "min": 0.00011228306257279998, "max": 0.0035082971305676995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249514666666666, "min": 0.10249514666666666, "max": 0.1982832625, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374272, "min": 1.4778482000000002, "max": 2.569432300000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025926515199999994, "min": 0.00025926515199999994, "max": 0.00982849792375, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038889772799999994, "min": 0.0038889772799999994, "max": 0.11696628677, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009291877038776875, "min": 0.009291877038776875, "max": 0.3609068989753723, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.139378160238266, "min": 0.13516680896282196, "max": 2.8872551918029785, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 426.06849315068496, "min": 426.06849315068496, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31103.0, "min": 16408.0, "max": 33110.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4395972785313387, "min": -1.0000000521540642, "max": 1.4395972785313387, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 106.53019861131907, "min": -32.000001668930054, "max": 106.53019861131907, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4395972785313387, "min": -1.0000000521540642, "max": 1.4395972785313387, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 106.53019861131907, "min": -32.000001668930054, "max": 106.53019861131907, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04160923832465857, "min": 0.04160923832465857, "max": 7.0314813720829346, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.079083636024734, "min": 2.8366092197793478, "max": 119.53518332540989, "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": "1705239242", "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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1705241348" }, "total": 2106.295075121, "count": 1, "self": 0.4973215660002097, "children": { "run_training.setup": { "total": 0.05525443300007282, "count": 1, "self": 0.05525443300007282 }, "TrainerController.start_learning": { "total": 2105.7424991219996, "count": 1, "self": 1.2892435439839574, "children": { "TrainerController._reset_env": { "total": 3.711053306999929, "count": 1, "self": 3.711053306999929 }, "TrainerController.advance": { "total": 2100.6577858460155, "count": 63633, "self": 1.3954062430389058, "children": { "env_step": { "total": 1465.8542416980613, "count": 63633, "self": 1336.6276414641065, "children": { "SubprocessEnvManager._take_step": { "total": 128.4213399959907, "count": 63633, "self": 4.531265455960352, "children": { "TorchPolicy.evaluate": { "total": 123.89007454003035, "count": 62560, "self": 123.89007454003035 } } }, "workers": { "total": 0.8052602379640348, "count": 63633, "self": 0.0, "children": { "worker_root": { "total": 2100.5470169859695, "count": 63633, "is_parallel": true, "self": 880.3268230579652, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005249089999892931, "count": 1, "is_parallel": true, "self": 0.003978396999855249, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012706930000376815, "count": 8, "is_parallel": true, "self": 0.0012706930000376815 } } }, "UnityEnvironment.step": { "total": 0.07944241400002738, "count": 1, "is_parallel": true, "self": 0.0006884320000608568, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004968079999798647, "count": 1, "is_parallel": true, "self": 0.0004968079999798647 }, "communicator.exchange": { "total": 0.0766087399999833, "count": 1, "is_parallel": true, "self": 0.0766087399999833 }, "steps_from_proto": { "total": 0.0016484340000033626, "count": 1, "is_parallel": true, "self": 0.00035488300011365936, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012935509998897032, "count": 8, "is_parallel": true, "self": 0.0012935509998897032 } } } } } } }, "UnityEnvironment.step": { "total": 1220.2201939280044, "count": 63632, "is_parallel": true, "self": 35.666214689050776, "children": { "UnityEnvironment._generate_step_input": { "total": 23.908050486992124, "count": 63632, "is_parallel": true, "self": 23.908050486992124 }, "communicator.exchange": { "total": 1063.4612812809926, "count": 63632, "is_parallel": true, "self": 1063.4612812809926 }, "steps_from_proto": { "total": 97.18464747096903, "count": 63632, "is_parallel": true, "self": 19.184797764961218, "children": { "_process_rank_one_or_two_observation": { "total": 77.99984970600781, "count": 509056, "is_parallel": true, "self": 77.99984970600781 } } } } } } } } } } }, "trainer_advance": { "total": 633.4081379049154, "count": 63633, "self": 2.6539706859081207, "children": { "process_trajectory": { "total": 125.35856744701096, "count": 63633, "self": 125.11705378801071, "children": { "RLTrainer._checkpoint": { "total": 0.24151365900024757, "count": 2, "self": 0.24151365900024757 } } }, "_update_policy": { "total": 505.39559977199633, "count": 454, "self": 298.8098523129986, "children": { "TorchPPOOptimizer.update": { "total": 206.58574745899773, "count": 22770, "self": 206.58574745899773 } } } } } } }, "trainer_threads": { "total": 8.189999789465219e-07, "count": 1, "self": 8.189999789465219e-07 }, "TrainerController._save_models": { "total": 0.08441560600022058, "count": 1, "self": 0.0014164580002216098, "children": { "RLTrainer._checkpoint": { "total": 0.08299914799999897, "count": 1, "self": 0.08299914799999897 } } } } } } }