{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5703490972518921, "min": 0.5494472980499268, "max": 1.4027103185653687, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17101.34765625, "min": 16562.5390625, "max": 42552.62109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989997.0, "min": 29952.0, "max": 989997.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989997.0, "min": 29952.0, "max": 989997.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.09232138842344284, "min": -0.12184180319309235, "max": 0.09232138842344284, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 22.988025665283203, "min": -28.876506805419922, "max": 22.988025665283203, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013315600343048573, "min": 0.007485616020858288, "max": 0.4585472345352173, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.315584421157837, "min": 1.8264902830123901, "max": 108.67569732666016, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06612502732708131, "min": 0.06429373416306969, "max": 0.07457556224764238, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9257503825791383, "min": 0.5012756362031368, "max": 1.049068538531976, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.006806938070403141, "min": 0.00013274726171743837, "max": 0.01624260973897305, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.09529713298564398, "min": 0.0017257144023266986, "max": 0.11369826817281137, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.546790341578573e-06, "min": 7.546790341578573e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010565506478210003, "min": 0.00010565506478210003, "max": 0.0035071946309352, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025155642857143, "min": 0.1025155642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352179000000003, "min": 1.3886848, "max": 2.5690648, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002613048721428573, "min": 0.0002613048721428573, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003658268210000002, "min": 0.003658268210000002, "max": 0.11692957352, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014894582331180573, "min": 0.014894582331180573, "max": 0.5332163572311401, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20852415263652802, "min": 0.20852415263652802, "max": 3.7325146198272705, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 737.3255813953489, "min": 737.3255813953489, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31705.0, "min": 15984.0, "max": 32528.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.28570693956558096, "min": -1.0000000521540642, "max": 0.28570693956558096, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 12.28539840131998, "min": -31.994401648640633, "max": 12.28539840131998, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.28570693956558096, "min": -1.0000000521540642, "max": 0.28570693956558096, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 12.28539840131998, "min": -31.994401648640633, "max": 12.28539840131998, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.1159303622553125, "min": 0.1159303622553125, "max": 11.660213833674788, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.985005576978438, "min": 4.483415444614366, "max": 186.56342133879662, "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": "1759783143", "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [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", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1759785239" }, "total": 2096.077959533999, "count": 1, "self": 0.4292326389977461, "children": { "run_training.setup": { "total": 0.016560984000534518, "count": 1, "self": 0.016560984000534518 }, "TrainerController.start_learning": { "total": 2095.632165911001, "count": 1, "self": 1.3077462239789384, "children": { "TrainerController._reset_env": { "total": 1.6186284680006793, "count": 1, "self": 1.6186284680006793 }, "TrainerController.advance": { "total": 2092.6537368150202, "count": 63283, "self": 1.3465351380928041, "children": { "env_step": { "total": 1369.5665481859487, "count": 63283, "self": 1271.5928540321793, "children": { "SubprocessEnvManager._take_step": { "total": 97.20022819699898, "count": 63283, "self": 4.6554433552519185, "children": { "TorchPolicy.evaluate": { "total": 92.54478484174706, "count": 62552, "self": 92.54478484174706 } } }, "workers": { "total": 0.7734659567704512, "count": 63283, "self": 0.0, "children": { "worker_root": { "total": 2090.506994118112, "count": 63283, "is_parallel": true, "self": 933.0590825298386, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023786649999237852, "count": 1, "is_parallel": true, "self": 0.0007521420011471491, "children": { "_process_rank_one_or_two_observation": { "total": 0.001626522998776636, "count": 8, "is_parallel": true, "self": 0.001626522998776636 } } }, "UnityEnvironment.step": { "total": 0.04664285899980314, "count": 1, "is_parallel": true, "self": 0.0005312780003805528, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004587119992720545, "count": 1, "is_parallel": true, "self": 0.0004587119992720545 }, "communicator.exchange": { "total": 0.04399000400007935, "count": 1, "is_parallel": true, "self": 0.04399000400007935 }, "steps_from_proto": { "total": 0.0016628650000711787, "count": 1, "is_parallel": true, "self": 0.0003587480014175526, "children": { "_process_rank_one_or_two_observation": { "total": 0.001304116998653626, "count": 8, "is_parallel": true, "self": 0.001304116998653626 } } } } } } }, "UnityEnvironment.step": { "total": 1157.4479115882732, "count": 63282, "is_parallel": true, "self": 32.63660534833434, "children": { "UnityEnvironment._generate_step_input": { "total": 23.34338906888661, "count": 63282, "is_parallel": true, "self": 23.34338906888661 }, "communicator.exchange": { "total": 986.3345122918918, "count": 63282, "is_parallel": true, "self": 986.3345122918918 }, "steps_from_proto": { "total": 115.13340487916048, "count": 63282, "is_parallel": true, "self": 25.490181528660287, "children": { "_process_rank_one_or_two_observation": { "total": 89.6432233505002, "count": 506256, "is_parallel": true, "self": 89.6432233505002 } } } } } } } } } } }, "trainer_advance": { "total": 721.7406534909787, "count": 63283, "self": 2.3948062549025053, "children": { "process_trajectory": { "total": 118.50225092205801, "count": 63283, "self": 118.29783259005853, "children": { "RLTrainer._checkpoint": { "total": 0.20441833199947723, "count": 2, "self": 0.20441833199947723 } } }, "_update_policy": { "total": 600.8435963140182, "count": 449, "self": 282.71514406496317, "children": { "TorchPPOOptimizer.update": { "total": 318.12845224905504, "count": 22788, "self": 318.12845224905504 } } } } } } }, "trainer_threads": { "total": 9.739997040014714e-07, "count": 1, "self": 9.739997040014714e-07 }, "TrainerController._save_models": { "total": 0.0520534300012514, "count": 1, "self": 0.0010650080021150643, "children": { "RLTrainer._checkpoint": { "total": 0.050988421999136335, "count": 1, "self": 0.050988421999136335 } } } } } } }