{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4545828104019165, "min": 0.44756296277046204, "max": 1.4014147520065308, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13499.291015625, "min": 13477.015625, "max": 42513.31640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5648380517959595, "min": -0.10371988266706467, "max": 0.6048298478126526, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 157.0249786376953, "min": -25.10021209716797, "max": 167.53787231445312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06576859951019287, "min": -0.03014148771762848, "max": 0.29793158173561096, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 18.28367042541504, "min": -8.198484420776367, "max": 70.60978698730469, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06866601122071522, "min": 0.06555687482998389, "max": 0.0730243159333728, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9613241570900131, "min": 0.48563084530312267, "max": 1.0346474225128381, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01725112739404212, "min": 6.373960285228172e-05, "max": 0.01725112739404212, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24151578351658967, "min": 0.0008286148370796624, "max": 0.2584892739444816, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.498426071985713e-06, "min": 7.498426071985713e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010497796500779998, "min": 0.00010497796500779998, "max": 0.003507302330899299, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249944285714285, "min": 0.10249944285714285, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349922, "min": 1.3886848, "max": 2.5691007000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025969434142857143, "min": 0.00025969434142857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00363572078, "min": 0.00363572078, "max": 0.11693315993, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009791119955480099, "min": 0.009791119955480099, "max": 0.4696134626865387, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13707567751407623, "min": 0.13707567751407623, "max": 3.2872941493988037, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 328.96774193548384, "min": 315.61052631578946, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30594.0, "min": 15984.0, "max": 32677.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6072574301444469, "min": -1.0000000521540642, "max": 1.6671733131011328, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 151.08219843357801, "min": -31.998001664876938, "max": 154.39499823749065, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6072574301444469, "min": -1.0000000521540642, "max": 1.6671733131011328, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 151.08219843357801, "min": -31.998001664876938, "max": 154.39499823749065, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.033248751541364946, "min": 0.03282072911183895, "max": 9.525055488571525, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1253826448883046, "min": 2.99098867392604, "max": 152.4008878171444, "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": "1731422568", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=/content/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --torch-device cuda:0 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1731425891" }, "total": 3323.5883038699976, "count": 1, "self": 0.6412247959815431, "children": { "run_training.setup": { "total": 0.07178426900645718, "count": 1, "self": 0.07178426900645718 }, "TrainerController.start_learning": { "total": 3322.8752948050096, "count": 1, "self": 2.0903676559973974, "children": { "TrainerController._reset_env": { "total": 7.014824181998847, "count": 1, "self": 7.014824181998847 }, "TrainerController.advance": { "total": 3313.6378221390187, "count": 63754, "self": 2.1330468476226088, "children": { "env_step": { "total": 2293.4892628269445, "count": 63754, "self": 1910.686466169107, "children": { "SubprocessEnvManager._take_step": { "total": 381.4046178472345, "count": 63754, "self": 7.2681120119814295, "children": { "TorchPolicy.evaluate": { "total": 374.13650583525305, "count": 62551, "self": 374.13650583525305 } } }, "workers": { "total": 1.3981788106029853, "count": 63754, "self": 0.0, "children": { "worker_root": { "total": 3318.5578395667253, "count": 63754, "is_parallel": true, "self": 1559.767075358308, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003901556017808616, "count": 1, "is_parallel": true, "self": 0.0013394920388236642, "children": { "_process_rank_one_or_two_observation": { "total": 0.002562063978984952, "count": 8, "is_parallel": true, "self": 0.002562063978984952 } } }, "UnityEnvironment.step": { "total": 0.042057195998495445, "count": 1, "is_parallel": true, "self": 0.0004932339652441442, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00025315902894362807, "count": 1, "is_parallel": true, "self": 0.00025315902894362807 }, "communicator.exchange": { "total": 0.04034303198568523, "count": 1, "is_parallel": true, "self": 0.04034303198568523 }, "steps_from_proto": { "total": 0.0009677710186224431, "count": 1, "is_parallel": true, "self": 0.00025191300665028393, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007158580119721591, "count": 8, "is_parallel": true, "self": 0.0007158580119721591 } } } } } } }, "UnityEnvironment.step": { "total": 1758.7907642084174, "count": 63753, "is_parallel": true, "self": 28.44468734957627, "children": { "UnityEnvironment._generate_step_input": { "total": 17.1521518373047, "count": 63753, "is_parallel": true, "self": 17.1521518373047 }, "communicator.exchange": { "total": 1636.7524044138263, "count": 63753, "is_parallel": true, "self": 1636.7524044138263 }, "steps_from_proto": { "total": 76.44152060771012, "count": 63753, "is_parallel": true, "self": 18.690734163217712, "children": { "_process_rank_one_or_two_observation": { "total": 57.750786444492405, "count": 510024, "is_parallel": true, "self": 57.750786444492405 } } } } } } } } } } }, "trainer_advance": { "total": 1018.0155124644516, "count": 63754, "self": 3.751149122515926, "children": { "process_trajectory": { "total": 199.16532345392625, "count": 63754, "self": 198.78596571393427, "children": { "RLTrainer._checkpoint": { "total": 0.3793577399919741, "count": 2, "self": 0.3793577399919741 } } }, "_update_policy": { "total": 815.0990398880094, "count": 444, "self": 403.34104048935114, "children": { "TorchPPOOptimizer.update": { "total": 411.7579993986583, "count": 22863, "self": 411.7579993986583 } } } } } } }, "trainer_threads": { "total": 1.955981133505702e-06, "count": 1, "self": 1.955981133505702e-06 }, "TrainerController._save_models": { "total": 0.1322788720135577, "count": 1, "self": 0.0020107979944441468, "children": { "RLTrainer._checkpoint": { "total": 0.13026807401911356, "count": 1, "self": 0.13026807401911356 } } } } } } }