{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.482870876789093, "min": 0.4660654366016388, "max": 1.423977017402649, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14625.193359375, "min": 13892.478515625, "max": 43197.765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989942.0, "min": 29952.0, "max": 989942.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989942.0, "min": 29952.0, "max": 989942.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.30509522557258606, "min": -0.10748226195573807, "max": 0.3991946280002594, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 79.62985229492188, "min": -25.79574203491211, "max": 104.5889892578125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.028714289888739586, "min": 0.018540622666478157, "max": 0.4508693516254425, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.494429588317871, "min": 4.523911952972412, "max": 106.85603332519531, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06824754029499362, "min": 0.06643238850215095, "max": 0.07328681995486809, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9554655641299107, "min": 0.5094016390627158, "max": 1.0820404452422414, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013961639381615858, "min": 0.00011424037334265057, "max": 0.014522429857087057, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.195462951342622, "min": 0.001599365226797108, "max": 0.2033140179992188, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.78023312090714e-06, "min": 7.78023312090714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010892326369269996, "min": 0.00010892326369269996, "max": 0.0036320845893052, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025933785714286, "min": 0.1025933785714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4363073000000004, "min": 1.3886848, "max": 2.6106948, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026907851928571427, "min": 0.00026907851928571427, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037670992699999997, "min": 0.0037670992699999997, "max": 0.12108841051999997, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012940873391926289, "min": 0.012940873391926289, "max": 0.4904060363769531, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1811722218990326, "min": 0.1811722218990326, "max": 3.432842254638672, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 497.52542372881356, "min": 464.73015873015873, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29354.0, "min": 15984.0, "max": 32515.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1972779366424529, "min": -1.0000000521540642, "max": 1.3829624792560935, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 70.63939826190472, "min": -30.545601658523083, "max": 88.50959867238998, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1972779366424529, "min": -1.0000000521540642, "max": 1.3829624792560935, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 70.63939826190472, "min": -30.545601658523083, "max": 88.50959867238998, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06626442493676624, "min": 0.06626442493676624, "max": 10.27092064730823, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9096010712692078, "min": 3.9096010712692078, "max": 164.3347303569317, "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": "1765395369", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/miniconda/envs/mlagents_env/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1765397414" }, "total": 2044.4756422720002, "count": 1, "self": 0.4758292470005472, "children": { "run_training.setup": { "total": 0.018967104999319417, "count": 1, "self": 0.018967104999319417 }, "TrainerController.start_learning": { "total": 2043.9808459200003, "count": 1, "self": 1.161222589935278, "children": { "TrainerController._reset_env": { "total": 2.1186500639996666, "count": 1, "self": 2.1186500639996666 }, "TrainerController.advance": { "total": 2040.6293348290646, "count": 63416, "self": 1.209581049015469, "children": { "env_step": { "total": 1397.7747889600341, "count": 63416, "self": 1260.148979923115, "children": { "SubprocessEnvManager._take_step": { "total": 136.91392191697923, "count": 63416, "self": 4.250105128076029, "children": { "TorchPolicy.evaluate": { "total": 132.6638167889032, "count": 62562, "self": 132.6638167889032 } } }, "workers": { "total": 0.7118871199400019, "count": 63416, "self": 0.0, "children": { "worker_root": { "total": 2037.0646026150516, "count": 63416, "is_parallel": true, "self": 885.3025405519611, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018030609999186709, "count": 1, "is_parallel": true, "self": 0.0005739959970014752, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012290650029171957, "count": 8, "is_parallel": true, "self": 0.0012290650029171957 } } }, "UnityEnvironment.step": { "total": 0.07161753899981704, "count": 1, "is_parallel": true, "self": 0.000517622999723244, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004704279999714345, "count": 1, "is_parallel": true, "self": 0.0004704279999714345 }, "communicator.exchange": { "total": 0.06893901500006905, "count": 1, "is_parallel": true, "self": 0.06893901500006905 }, "steps_from_proto": { "total": 0.0016904730000533164, "count": 1, "is_parallel": true, "self": 0.00040774500030238414, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012827279997509322, "count": 8, "is_parallel": true, "self": 0.0012827279997509322 } } } } } } }, "UnityEnvironment.step": { "total": 1151.7620620630905, "count": 63415, "is_parallel": true, "self": 32.25678311611591, "children": { "UnityEnvironment._generate_step_input": { "total": 21.887586937008564, "count": 63415, "is_parallel": true, "self": 21.887586937008564 }, "communicator.exchange": { "total": 997.8075564680594, "count": 63415, "is_parallel": true, "self": 997.8075564680594 }, "steps_from_proto": { "total": 99.81013554190667, "count": 63415, "is_parallel": true, "self": 20.3404815251115, "children": { "_process_rank_one_or_two_observation": { "total": 79.46965401679518, "count": 507320, "is_parallel": true, "self": 79.46965401679518 } } } } } } } } } } }, "trainer_advance": { "total": 641.644964820015, "count": 63416, "self": 2.2735409029673974, "children": { "process_trajectory": { "total": 117.50694208304503, "count": 63416, "self": 117.31395987604446, "children": { "RLTrainer._checkpoint": { "total": 0.19298220700056845, "count": 2, "self": 0.19298220700056845 } } }, "_update_policy": { "total": 521.8644818340026, "count": 450, "self": 292.5928180410465, "children": { "TorchPPOOptimizer.update": { "total": 229.27166379295613, "count": 22827, "self": 229.27166379295613 } } } } } } }, "trainer_threads": { "total": 8.220004019676708e-07, "count": 1, "self": 8.220004019676708e-07 }, "TrainerController._save_models": { "total": 0.07163761500032706, "count": 1, "self": 0.0010158980003325269, "children": { "RLTrainer._checkpoint": { "total": 0.07062171699999453, "count": 1, "self": 0.07062171699999453 } } } } } } }