{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.585995614528656, "min": 0.5724242925643921, "max": 1.4841898679733276, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17711.130859375, "min": 17163.5703125, "max": 45024.3828125, "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": 0.3008681833744049, "min": -0.16077439486980438, "max": 0.3008681833744049, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 77.3231201171875, "min": -38.10353088378906, "max": 77.3231201171875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.023835860192775726, "min": 0.0035970662720501423, "max": 0.3309265673160553, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.1258158683776855, "min": 0.8812812566757202, "max": 78.42959594726562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06599930190436898, "min": 0.06599930190436898, "max": 0.07319374297146955, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9239902266611657, "min": 0.5012008020709183, "max": 1.034793000513067, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010911149064018643, "min": 4.4621544612611985e-05, "max": 0.012725259800225036, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.152756086896261, "min": 0.0005800800799639558, "max": 0.1781536372031505, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.668804586621425e-06, "min": 7.668804586621425e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010736326421269996, "min": 0.00010736326421269996, "max": 0.0031370306543231996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255623571428572, "min": 0.10255623571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357873, "min": 1.3886848, "max": 2.3456768, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026536794785714284, "min": 0.00026536794785714284, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037151512699999997, "min": 0.0037151512699999997, "max": 0.10459311231999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01263519935309887, "min": 0.012556752189993858, "max": 0.42222410440444946, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17689278721809387, "min": 0.17579452693462372, "max": 2.955568790435791, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 578.811320754717, "min": 513.3898305084746, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30677.0, "min": 15984.0, "max": 32929.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.081445261414321, "min": -1.0000000521540642, "max": 1.145099971195062, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 57.31659885495901, "min": -31.999601677060127, "max": 68.70599827170372, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.081445261414321, "min": -1.0000000521540642, "max": 1.145099971195062, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 57.31659885495901, "min": -31.999601677060127, "max": 68.70599827170372, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07499322810134508, "min": 0.06749817883537616, "max": 9.227673852816224, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.974641089371289, "min": 3.717119455570355, "max": 147.64278164505959, "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": "1736357212", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736359451" }, "total": 2238.7710009730004, "count": 1, "self": 0.8706518850003704, "children": { "run_training.setup": { "total": 0.06618562799997108, "count": 1, "self": 0.06618562799997108 }, "TrainerController.start_learning": { "total": 2237.83416346, "count": 1, "self": 1.5518978120403517, "children": { "TrainerController._reset_env": { "total": 2.31406687599997, "count": 1, "self": 2.31406687599997 }, "TrainerController.advance": { "total": 2233.83277094596, "count": 63298, "self": 1.5370866959610794, "children": { "env_step": { "total": 1513.3757435110317, "count": 63298, "self": 1349.1345265591563, "children": { "SubprocessEnvManager._take_step": { "total": 163.32271767895236, "count": 63298, "self": 5.089585431958085, "children": { "TorchPolicy.evaluate": { "total": 158.23313224699427, "count": 62563, "self": 158.23313224699427 } } }, "workers": { "total": 0.9184992729232135, "count": 63298, "self": 0.0, "children": { "worker_root": { "total": 2232.088338433969, "count": 63298, "is_parallel": true, "self": 1013.1655242579886, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021525220000739864, "count": 1, "is_parallel": true, "self": 0.0006605109998645275, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014920110002094589, "count": 8, "is_parallel": true, "self": 0.0014920110002094589 } } }, "UnityEnvironment.step": { "total": 0.07188446399993609, "count": 1, "is_parallel": true, "self": 0.0006749159999799303, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004198679999944943, "count": 1, "is_parallel": true, "self": 0.0004198679999944943 }, "communicator.exchange": { "total": 0.06921163100003014, "count": 1, "is_parallel": true, "self": 0.06921163100003014 }, "steps_from_proto": { "total": 0.001578048999931525, "count": 1, "is_parallel": true, "self": 0.0003222540001388552, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012557949997926698, "count": 8, "is_parallel": true, "self": 0.0012557949997926698 } } } } } } }, "UnityEnvironment.step": { "total": 1218.9228141759804, "count": 63297, "is_parallel": true, "self": 35.131908818010515, "children": { "UnityEnvironment._generate_step_input": { "total": 24.754050596003594, "count": 63297, "is_parallel": true, "self": 24.754050596003594 }, "communicator.exchange": { "total": 1052.5949863150188, "count": 63297, "is_parallel": true, "self": 1052.5949863150188 }, "steps_from_proto": { "total": 106.44186844694764, "count": 63297, "is_parallel": true, "self": 22.27961402996084, "children": { "_process_rank_one_or_two_observation": { "total": 84.1622544169868, "count": 506376, "is_parallel": true, "self": 84.1622544169868 } } } } } } } } } } }, "trainer_advance": { "total": 718.9199407389674, "count": 63298, "self": 2.694874501934464, "children": { "process_trajectory": { "total": 139.12675643802913, "count": 63298, "self": 138.8033797700291, "children": { "RLTrainer._checkpoint": { "total": 0.32337666800003717, "count": 2, "self": 0.32337666800003717 } } }, "_update_policy": { "total": 577.0983097990038, "count": 436, "self": 325.87893009000584, "children": { "TorchPPOOptimizer.update": { "total": 251.21937970899796, "count": 22866, "self": 251.21937970899796 } } } } } } }, "trainer_threads": { "total": 1.2800001059076749e-06, "count": 1, "self": 1.2800001059076749e-06 }, "TrainerController._save_models": { "total": 0.1354265459999624, "count": 1, "self": 0.002293628000188619, "children": { "RLTrainer._checkpoint": { "total": 0.13313291799977378, "count": 1, "self": 0.13313291799977378 } } } } } } }