{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4147973954677582, "min": 0.4147973954677582, "max": 1.5070947408676147, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12430.6484375, "min": 12430.6484375, "max": 45719.2265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4002164900302887, "min": -0.18761074542999268, "max": 0.49450740218162537, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 106.45758819580078, "min": -44.4637451171875, "max": 133.51699829101562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0013132758904248476, "min": -0.041792262345552444, "max": 0.2864011526107788, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.3493313789367676, "min": -11.074949264526367, "max": 67.8770751953125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06836717138729673, "min": 0.06466520525420838, "max": 0.07276311304760348, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9571403994221542, "min": 0.4857650223487839, "max": 1.0600841455481143, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013215285690958839, "min": 0.000775465734121976, "max": 0.014347434104783566, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18501399967342375, "min": 0.009473732503893582, "max": 0.2152115115717535, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.460004656221427e-06, "min": 7.460004656221427e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010444006518709998, "min": 0.00010444006518709998, "max": 0.003253358915547099, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248663571428572, "min": 0.10248663571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348129, "min": 1.3886848, "max": 2.4441072, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002584149078571428, "min": 0.0002584149078571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036178087099999995, "min": 0.0036178087099999995, "max": 0.10846684471000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01563427783548832, "min": 0.01563427783548832, "max": 0.4344734847545624, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21887989342212677, "min": 0.21887989342212677, "max": 3.0413143634796143, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 422.4848484848485, "min": 392.0133333333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27884.0, "min": 15984.0, "max": 32553.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3350272436033597, "min": -1.0000000521540642, "max": 1.5350856910858834, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 88.11179807782173, "min": -29.857401683926582, "max": 111.45779855549335, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3350272436033597, "min": -1.0000000521540642, "max": 1.5350856910858834, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 88.11179807782173, "min": -29.857401683926582, "max": 111.45779855549335, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06859261301173264, "min": 0.06540550023153727, "max": 8.747810463421047, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.527112458774354, "min": 4.527112458774354, "max": 139.96496741473675, "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": "1723283440", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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 1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723285546" }, "total": 2105.5707972329997, "count": 1, "self": 0.48884097699965423, "children": { "run_training.setup": { "total": 0.0519811970000319, "count": 1, "self": 0.0519811970000319 }, "TrainerController.start_learning": { "total": 2105.0299750589998, "count": 1, "self": 1.218900079046307, "children": { "TrainerController._reset_env": { "total": 2.157403357000021, "count": 1, "self": 2.157403357000021 }, "TrainerController.advance": { "total": 2101.5684402359534, "count": 63613, "self": 1.2713414550617017, "children": { "env_step": { "total": 1481.28680306896, "count": 63613, "self": 1357.4453752651077, "children": { "SubprocessEnvManager._take_step": { "total": 123.05988234194888, "count": 63613, "self": 4.4623728459569065, "children": { "TorchPolicy.evaluate": { "total": 118.59750949599197, "count": 62562, "self": 118.59750949599197 } } }, "workers": { "total": 0.7815454619033062, "count": 63613, "self": 0.0, "children": { "worker_root": { "total": 2100.441605283011, "count": 63613, "is_parallel": true, "self": 856.9754999360443, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020442019999791228, "count": 1, "is_parallel": true, "self": 0.0006482810001671169, "children": { "_process_rank_one_or_two_observation": { "total": 0.001395920999812006, "count": 8, "is_parallel": true, "self": 0.001395920999812006 } } }, "UnityEnvironment.step": { "total": 0.046878160000005664, "count": 1, "is_parallel": true, "self": 0.0006019429999923886, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004614479998963361, "count": 1, "is_parallel": true, "self": 0.0004614479998963361 }, "communicator.exchange": { "total": 0.044003400000065085, "count": 1, "is_parallel": true, "self": 0.044003400000065085 }, "steps_from_proto": { "total": 0.0018113690000518545, "count": 1, "is_parallel": true, "self": 0.000380033999817897, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014313350002339575, "count": 8, "is_parallel": true, "self": 0.0014313350002339575 } } } } } } }, "UnityEnvironment.step": { "total": 1243.4661053469667, "count": 63612, "is_parallel": true, "self": 32.1613023770567, "children": { "UnityEnvironment._generate_step_input": { "total": 21.447148767969566, "count": 63612, "is_parallel": true, "self": 21.447148767969566 }, "communicator.exchange": { "total": 1096.7453665510147, "count": 63612, "is_parallel": true, "self": 1096.7453665510147 }, "steps_from_proto": { "total": 93.11228765092574, "count": 63612, "is_parallel": true, "self": 18.217883951903104, "children": { "_process_rank_one_or_two_observation": { "total": 74.89440369902263, "count": 508896, "is_parallel": true, "self": 74.89440369902263 } } } } } } } } } } }, "trainer_advance": { "total": 619.0102957119318, "count": 63613, "self": 2.4436368579492864, "children": { "process_trajectory": { "total": 125.37654072798705, "count": 63613, "self": 125.1844067329871, "children": { "RLTrainer._checkpoint": { "total": 0.1921339949999492, "count": 2, "self": 0.1921339949999492 } } }, "_update_policy": { "total": 491.19011812599547, "count": 448, "self": 290.2127225049976, "children": { "TorchPPOOptimizer.update": { "total": 200.97739562099787, "count": 22845, "self": 200.97739562099787 } } } } } } }, "trainer_threads": { "total": 9.219997991749551e-07, "count": 1, "self": 9.219997991749551e-07 }, "TrainerController._save_models": { "total": 0.08523046500022247, "count": 1, "self": 0.0013106420001349761, "children": { "RLTrainer._checkpoint": { "total": 0.08391982300008749, "count": 1, "self": 0.08391982300008749 } } } } } } }