{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4428914189338684, "min": 0.4428914189338684, "max": 1.4335201978683472, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13308.0009765625, "min": 13308.0009765625, "max": 43487.26953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.524365246295929, "min": -0.09930995851755142, "max": 0.5550134778022766, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 146.822265625, "min": -23.83439064025879, "max": 154.8487548828125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.003061752999201417, "min": -0.06743450462818146, "max": 0.28995344042778015, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.8572908639907837, "min": -18.477054595947266, "max": 68.71896362304688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06949498285280747, "min": 0.06517484901641082, "max": 0.07464399516973964, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.042424742792112, "min": 0.48777097151025955, "max": 1.0675947509977657, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01541273717949581, "min": 0.00033963280511144244, "max": 0.015687364884787527, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23119105769243714, "min": 0.004075593661337309, "max": 0.23119105769243714, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.582877472406667e-06, "min": 7.582877472406667e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001137431620861, "min": 0.0001137431620861, "max": 0.0036096207967930994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252759333333336, "min": 0.10252759333333336, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5379139000000004, "min": 1.3886848, "max": 2.5032069, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026250657400000006, "min": 0.00026250657400000006, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003937598610000001, "min": 0.003937598610000001, "max": 0.12033036931000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01009493786841631, "min": 0.00989051628857851, "max": 0.38469764590263367, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15142406523227692, "min": 0.1384672224521637, "max": 2.6928834915161133, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 340.69662921348316, "min": 340.69662921348316, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30322.0, "min": 15984.0, "max": 33368.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5694044734654802, "min": -1.0000000521540642, "max": 1.570194178733273, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 139.67699813842773, "min": -29.998401559889317, "max": 139.67699813842773, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5694044734654802, "min": -1.0000000521540642, "max": 1.570194178733273, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 139.67699813842773, "min": -29.998401559889317, "max": 139.67699813842773, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.035075204382981486, "min": 0.035075204382981486, "max": 7.523131267167628, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1216931900853524, "min": 2.990722785354592, "max": 120.37010027468204, "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": "1739167099", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739170373" }, "total": 3273.592814341, "count": 1, "self": 0.6469643649998034, "children": { "run_training.setup": { "total": 0.05465175899996666, "count": 1, "self": 0.05465175899996666 }, "TrainerController.start_learning": { "total": 3272.8911982170002, "count": 1, "self": 2.3270588050186234, "children": { "TrainerController._reset_env": { "total": 4.559165635999989, "count": 1, "self": 4.559165635999989 }, "TrainerController.advance": { "total": 3265.909761824982, "count": 63671, "self": 2.5310432549777033, "children": { "env_step": { "total": 2141.9583583690282, "count": 63671, "self": 1970.3168366070345, "children": { "SubprocessEnvManager._take_step": { "total": 170.2174462800309, "count": 63671, "self": 7.3331047240052385, "children": { "TorchPolicy.evaluate": { "total": 162.88434155602567, "count": 62559, "self": 162.88434155602567 } } }, "workers": { "total": 1.4240754819628592, "count": 63671, "self": 0.0, "children": { "worker_root": { "total": 3265.441432671991, "count": 63671, "is_parallel": true, "self": 1473.663736878976, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.010189213999979074, "count": 1, "is_parallel": true, "self": 0.00707990999978847, "children": { "_process_rank_one_or_two_observation": { "total": 0.0031093040001906047, "count": 8, "is_parallel": true, "self": 0.0031093040001906047 } } }, "UnityEnvironment.step": { "total": 0.06913875700001881, "count": 1, "is_parallel": true, "self": 0.000713669999981903, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005669480000278782, "count": 1, "is_parallel": true, "self": 0.0005669480000278782 }, "communicator.exchange": { "total": 0.06548624800007019, "count": 1, "is_parallel": true, "self": 0.06548624800007019 }, "steps_from_proto": { "total": 0.0023718909999388416, "count": 1, "is_parallel": true, "self": 0.0006500689999029419, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017218220000358997, "count": 8, "is_parallel": true, "self": 0.0017218220000358997 } } } } } } }, "UnityEnvironment.step": { "total": 1791.7776957930153, "count": 63670, "is_parallel": true, "self": 47.77004331708895, "children": { "UnityEnvironment._generate_step_input": { "total": 30.953911682986927, "count": 63670, "is_parallel": true, "self": 30.953911682986927 }, "communicator.exchange": { "total": 1586.512564845938, "count": 63670, "is_parallel": true, "self": 1586.512564845938 }, "steps_from_proto": { "total": 126.54117594700142, "count": 63670, "is_parallel": true, "self": 27.49513827184512, "children": { "_process_rank_one_or_two_observation": { "total": 99.0460376751563, "count": 509360, "is_parallel": true, "self": 99.0460376751563 } } } } } } } } } } }, "trainer_advance": { "total": 1121.4203602009761, "count": 63671, "self": 4.7135477689412255, "children": { "process_trajectory": { "total": 165.9967078570387, "count": 63671, "self": 165.5726975390387, "children": { "RLTrainer._checkpoint": { "total": 0.42401031800000055, "count": 2, "self": 0.42401031800000055 } } }, "_update_policy": { "total": 950.7101045749962, "count": 451, "self": 367.5822639650088, "children": { "TorchPPOOptimizer.update": { "total": 583.1278406099874, "count": 22824, "self": 583.1278406099874 } } } } } } }, "trainer_threads": { "total": 9.539999155094847e-07, "count": 1, "self": 9.539999155094847e-07 }, "TrainerController._save_models": { "total": 0.09521099699986735, "count": 1, "self": 0.002019220999954996, "children": { "RLTrainer._checkpoint": { "total": 0.09319177599991235, "count": 1, "self": 0.09319177599991235 } } } } } } }