{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.38140636682510376, "min": 0.38140636682510376, "max": 1.4187757968902588, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11326.2431640625, "min": 11326.2431640625, "max": 43039.984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989957.0, "min": 29952.0, "max": 989957.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989957.0, "min": 29952.0, "max": 989957.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.615683913230896, "min": -0.09813455492258072, "max": 0.6360171437263489, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 176.08560180664062, "min": -23.257888793945312, "max": 180.62887573242188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008822066709399223, "min": -0.008176445960998535, "max": 0.39345797896385193, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.52311110496521, "min": -2.1585817337036133, "max": 95.21682739257812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06792076883837873, "min": 0.06383114627719706, "max": 0.07389647262650269, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9508907637373022, "min": 0.5066903433794271, "max": 1.0345506167710377, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01628765559802386, "min": 0.0024428520095780793, "max": 0.017383587327721113, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22802717837233405, "min": 0.02442852009578079, "max": 0.2607538099158167, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.425483239157141e-06, "min": 7.425483239157141e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010395676534819997, "min": 0.00010395676534819997, "max": 0.003635194988268399, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247512857142858, "min": 0.10247512857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346518000000001, "min": 1.3886848, "max": 2.6178095000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002572653442857142, "min": 0.0002572653442857142, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036017148199999987, "min": 0.0036017148199999987, "max": 0.12119198684, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013585503213107586, "min": 0.013224496506154537, "max": 0.623102605342865, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19019705057144165, "min": 0.18605610728263855, "max": 4.36171817779541, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 309.7307692307692, "min": 296.4895833333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32212.0, "min": 15984.0, "max": 33517.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6133249841200619, "min": -1.0000000521540642, "max": 1.682668734807521, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 167.78579834848642, "min": -27.548001766204834, "max": 167.78579834848642, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6133249841200619, "min": -1.0000000521540642, "max": 1.682668734807521, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 167.78579834848642, "min": -27.548001766204834, "max": 167.78579834848642, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.044333327822431996, "min": 0.0397010791023907, "max": 11.706958500668406, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.610666093532927, "min": 3.811303593829507, "max": 187.3113360106945, "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": "1725556953", "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 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1725559484" }, "total": 2531.3457745919995, "count": 1, "self": 0.48154797100005453, "children": { "run_training.setup": { "total": 0.050734612999804085, "count": 1, "self": 0.050734612999804085 }, "TrainerController.start_learning": { "total": 2530.8134920079997, "count": 1, "self": 1.4913104860315798, "children": { "TrainerController._reset_env": { "total": 1.790985868000007, "count": 1, "self": 1.790985868000007 }, "TrainerController.advance": { "total": 2527.4427934839678, "count": 64184, "self": 1.5528775050129298, "children": { "env_step": { "total": 1806.5453648679777, "count": 64184, "self": 1638.527926627091, "children": { "SubprocessEnvManager._take_step": { "total": 167.10367816695407, "count": 64184, "self": 5.035166381899671, "children": { "TorchPolicy.evaluate": { "total": 162.0685117850544, "count": 62555, "self": 162.0685117850544 } } }, "workers": { "total": 0.9137600739327354, "count": 64184, "self": 0.0, "children": { "worker_root": { "total": 2524.9137380160346, "count": 64184, "is_parallel": true, "self": 1019.3066873359862, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022815369998170354, "count": 1, "is_parallel": true, "self": 0.0007641009997314541, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015174360000855813, "count": 8, "is_parallel": true, "self": 0.0015174360000855813 } } }, "UnityEnvironment.step": { "total": 0.04966278899973986, "count": 1, "is_parallel": true, "self": 0.000623727999482071, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048624999999447027, "count": 1, "is_parallel": true, "self": 0.00048624999999447027 }, "communicator.exchange": { "total": 0.04685713200024111, "count": 1, "is_parallel": true, "self": 0.04685713200024111 }, "steps_from_proto": { "total": 0.00169567900002221, "count": 1, "is_parallel": true, "self": 0.00035109600003124797, "children": { "_process_rank_one_or_two_observation": { "total": 0.001344582999990962, "count": 8, "is_parallel": true, "self": 0.001344582999990962 } } } } } } }, "UnityEnvironment.step": { "total": 1505.6070506800484, "count": 64183, "is_parallel": true, "self": 35.221849494070284, "children": { "UnityEnvironment._generate_step_input": { "total": 24.82752141402716, "count": 64183, "is_parallel": true, "self": 24.82752141402716 }, "communicator.exchange": { "total": 1337.5329502050622, "count": 64183, "is_parallel": true, "self": 1337.5329502050622 }, "steps_from_proto": { "total": 108.02472956688871, "count": 64183, "is_parallel": true, "self": 22.5672799309491, "children": { "_process_rank_one_or_two_observation": { "total": 85.45744963593961, "count": 513464, "is_parallel": true, "self": 85.45744963593961 } } } } } } } } } } }, "trainer_advance": { "total": 719.3445511109771, "count": 64184, "self": 2.789161215926015, "children": { "process_trajectory": { "total": 143.08472742405047, "count": 64184, "self": 142.88103493105064, "children": { "RLTrainer._checkpoint": { "total": 0.20369249299983494, "count": 2, "self": 0.20369249299983494 } } }, "_update_policy": { "total": 573.4706624710007, "count": 458, "self": 323.87110531798135, "children": { "TorchPPOOptimizer.update": { "total": 249.5995571530193, "count": 22788, "self": 249.5995571530193 } } } } } } }, "trainer_threads": { "total": 1.2860000424552709e-06, "count": 1, "self": 1.2860000424552709e-06 }, "TrainerController._save_models": { "total": 0.08840088400029344, "count": 1, "self": 0.0013400650004768977, "children": { "RLTrainer._checkpoint": { "total": 0.08706081899981655, "count": 1, "self": 0.08706081899981655 } } } } } } }