{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8344421982765198, "min": 0.8344421982765198, "max": 1.4589592218399048, "count": 6 }, "Pyramids.Policy.Entropy.sum": { "value": 24993.212890625, "min": 24993.212890625, "max": 44258.98828125, "count": 6 }, "Pyramids.Step.mean": { "value": 179897.0, "min": 29952.0, "max": 179897.0, "count": 6 }, "Pyramids.Step.sum": { "value": 179897.0, "min": 29952.0, "max": 179897.0, "count": 6 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.06564684212207794, "min": -0.09134455770254135, "max": -0.06564684212207794, "count": 6 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -15.755241394042969, "min": -22.0140380859375, "max": -15.755241394042969, "count": 6 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.05716981738805771, "min": 0.05716981738805771, "max": 0.36287689208984375, "count": 6 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 13.720756530761719, "min": 13.720756530761719, "max": 86.00182342529297, "count": 6 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06959552754469676, "min": 0.06825836373480343, "max": 0.07304760388080911, "count": 6 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.904741858081058, "min": 0.5056347160305072, "max": 0.904741858081058, "count": 6 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.001525501104862326, "min": 0.0005431149656163833, "max": 0.005866744236660208, "count": 6 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.019831514363210238, "min": 0.00488803469054745, "max": 0.04106720965662146, "count": 6 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.3808543602307696e-05, "min": 5.3808543602307696e-05, "max": 0.00027575315093942855, "count": 6 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0006995110668300001, "min": 0.0006995110668300001, "max": 0.0020768957077014994, "count": 6 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.11793615384615387, "min": 0.11793615384615387, "max": 0.19191771428571427, "count": 6 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5331700000000004, "min": 1.343424, "max": 1.6311785, "count": 6 }, "Pyramids.Policy.Beta.mean": { "value": 0.0018018217692307693, "min": 0.0018018217692307693, "max": 0.009192579657142857, "count": 6 }, "Pyramids.Policy.Beta.sum": { "value": 0.023423683, "min": 0.023423683, "max": 0.06925062015, "count": 6 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.05492914468050003, "min": 0.05492914468050003, "max": 0.45118477940559387, "count": 6 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.7140789031982422, "min": 0.7140789031982422, "max": 3.1582934856414795, "count": 6 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 978.0, "min": 978.0, "max": 999.0, "count": 6 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31296.0, "min": 15984.0, "max": 31968.0, "count": 6 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8538500510621816, "min": -1.0000000521540642, "max": -0.8538500510621816, "count": 6 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -27.32320163398981, "min": -31.99920167028904, "max": -16.000000834465027, "count": 6 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8538500510621816, "min": -1.0000000521540642, "max": -0.8538500510621816, "count": 6 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -27.32320163398981, "min": -31.99920167028904, "max": -16.000000834465027, "count": 6 }, "Pyramids.Policy.RndReward.mean": { "value": 0.5607935880543664, "min": 0.5607935880543664, "max": 8.842708743177354, "count": 6 }, "Pyramids.Policy.RndReward.sum": { "value": 17.945394817739725, "min": 17.945394817739725, "max": 141.48333989083767, "count": 6 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677705346", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677705795" }, "total": 448.75241684499997, "count": 1, "self": 0.48661805800020375, "children": { "run_training.setup": { "total": 0.11014946399996006, "count": 1, "self": 0.11014946399996006 }, "TrainerController.start_learning": { "total": 448.1556493229998, "count": 1, "self": 0.27997033605583965, "children": { "TrainerController._reset_env": { "total": 7.413424659999919, "count": 1, "self": 7.413424659999919 }, "TrainerController.advance": { "total": 440.3566811069438, "count": 12570, "self": 0.30366000395338233, "children": { "env_step": { "total": 282.73606895298803, "count": 12570, "self": 257.5281279619812, "children": { "SubprocessEnvManager._take_step": { "total": 25.027103405010394, "count": 12570, "self": 1.0300886469774468, "children": { "TorchPolicy.evaluate": { "total": 23.997014758032947, "count": 12551, "self": 8.047531362996324, "children": { "TorchPolicy.sample_actions": { "total": 15.949483395036623, "count": 12551, "self": 15.949483395036623 } } } } }, "workers": { "total": 0.18083758599641442, "count": 12570, "self": 0.0, "children": { "worker_root": { "total": 447.0790659109664, "count": 12570, "is_parallel": true, "self": 214.77699432894497, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023816580001039256, "count": 1, "is_parallel": true, "self": 0.0008500230005665799, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015316349995373457, "count": 8, "is_parallel": true, "self": 0.0015316349995373457 } } }, "UnityEnvironment.step": { "total": 0.05234915000005458, "count": 1, "is_parallel": true, "self": 0.0006053399999927933, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005165669999769307, "count": 1, "is_parallel": true, "self": 0.0005165669999769307 }, "communicator.exchange": { "total": 0.04937572700009696, "count": 1, "is_parallel": true, "self": 0.04937572700009696 }, "steps_from_proto": { "total": 0.001851515999987896, "count": 1, "is_parallel": true, "self": 0.00043486200002007536, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014166539999678207, "count": 8, "is_parallel": true, "self": 0.0014166539999678207 } } } } } } }, "UnityEnvironment.step": { "total": 232.30207158202143, "count": 12569, "is_parallel": true, "self": 6.5830120529615215, "children": { "UnityEnvironment._generate_step_input": { "total": 5.160936496024988, "count": 12569, "is_parallel": true, "self": 5.160936496024988 }, "communicator.exchange": { "total": 200.05224824802076, "count": 12569, "is_parallel": true, "self": 200.05224824802076 }, "steps_from_proto": { "total": 20.505874785014157, "count": 12569, "is_parallel": true, "self": 4.913962686019204, "children": { "_process_rank_one_or_two_observation": { "total": 15.591912098994953, "count": 100552, "is_parallel": true, "self": 15.591912098994953 } } } } } } } } } } }, "trainer_advance": { "total": 157.3169521500024, "count": 12570, "self": 0.40983423701482025, "children": { "process_trajectory": { "total": 33.85925481098752, "count": 12570, "self": 33.85925481098752 }, "_update_policy": { "total": 123.04786310200006, "count": 69, "self": 47.835277925007176, "children": { "TorchPPOOptimizer.update": { "total": 75.21258517699289, "count": 4602, "self": 75.21258517699289 } } } } } } }, "trainer_threads": { "total": 9.43000031838892e-07, "count": 1, "self": 9.43000031838892e-07 }, "TrainerController._save_models": { "total": 0.10557227700019212, "count": 1, "self": 0.0014550250002685061, "children": { "RLTrainer._checkpoint": { "total": 0.10411725199992361, "count": 1, "self": 0.10411725199992361 } } } } } } }