{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2898765504360199, "min": 0.26469069719314575, "max": 1.5081944465637207, "count": 51 }, "Pyramids.Policy.Entropy.sum": { "value": 8691.658203125, "min": 7953.42578125, "max": 45752.5859375, "count": 51 }, "Pyramids.Step.mean": { "value": 1529981.0, "min": 29922.0, "max": 1529981.0, "count": 51 }, "Pyramids.Step.sum": { "value": 1529981.0, "min": 29922.0, "max": 1529981.0, "count": 51 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6767492294311523, "min": -0.11692368984222412, "max": 0.7353526949882507, "count": 51 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 193.55027770996094, "min": -27.710914611816406, "max": 213.25228881835938, "count": 51 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0003677794011309743, "min": -0.05105415731668472, "max": 0.19177569448947906, "count": 51 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.10518491268157959, "min": -13.97420597076416, "max": 46.02616500854492, "count": 51 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06948249490163844, "min": 0.06505522868454656, "max": 0.07415009922411878, "count": 51 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9727549286229381, "min": 0.5589093238752394, "max": 1.1122514883617816, "count": 51 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015288310141407973, "min": 0.0009200563268282316, "max": 0.015903870087294353, "count": 51 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21403634197971164, "min": 0.010057670258267214, "max": 0.2242328618594911, "count": 51 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00014849350050218332, "min": 0.00014849350050218332, "max": 0.00029828112557295835, "count": 51 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0020789090070305665, "min": 0.0020789090070305665, "max": 0.004072422942525733, "count": 51 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1494978166666667, "min": 0.1494978166666667, "max": 0.19942704166666667, "count": 51 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.0929694333333337, "min": 1.5954163333333333, "max": 2.8574742666666673, "count": 51 }, "Pyramids.Policy.Beta.mean": { "value": 0.004954831884999999, "min": 0.004954831884999999, "max": 0.0099427614625, "count": 51 }, "Pyramids.Policy.Beta.sum": { "value": 0.06936764639, "min": 0.06936764639, "max": 0.13576167924000002, "count": 51 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006303749047219753, "min": 0.005728147923946381, "max": 0.3313819169998169, "count": 51 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0882524847984314, "min": 0.08019407093524933, "max": 2.651055335998535, "count": 51 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 304.6372549019608, "min": 265.1810344827586, "max": 999.0, "count": 51 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31073.0, "min": 16465.0, "max": 33273.0, "count": 51 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.616901945249707, "min": -0.9999750521965325, "max": 1.717575851442485, "count": 51 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 164.92399841547012, "min": -31.99920167028904, "max": 199.23879876732826, "count": 51 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.616901945249707, "min": -0.9999750521965325, "max": 1.717575851442485, "count": 51 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 164.92399841547012, "min": -31.99920167028904, "max": 199.23879876732826, "count": 51 }, "Pyramids.Policy.RndReward.mean": { "value": 0.019882948195742097, "min": 0.017071139564685492, "max": 7.057126041720895, "count": 51 }, "Pyramids.Policy.RndReward.sum": { "value": 2.028060715965694, "min": 1.7885563879754045, "max": 119.97114270925522, "count": 51 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 51 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 51 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1791967934", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/content/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": "1791971174" }, "total": 3240.1432651799996, "count": 1, "self": 0.46470998499898997, "children": { "run_training.setup": { "total": 0.019263340000179596, "count": 1, "self": 0.019263340000179596 }, "TrainerController.start_learning": { "total": 3239.6592918550004, "count": 1, "self": 2.364023071059364, "children": { "TrainerController._reset_env": { "total": 2.14214676399979, "count": 1, "self": 2.14214676399979 }, "TrainerController.advance": { "total": 3235.1531220199413, "count": 98802, "self": 2.1215835297534795, "children": { "env_step": { "total": 2319.7706386231207, "count": 98802, "self": 2094.085907410041, "children": { "SubprocessEnvManager._take_step": { "total": 224.3771003179968, "count": 98802, "self": 7.120752235040982, "children": { "TorchPolicy.evaluate": { "total": 217.2563480829558, "count": 96109, "self": 217.2563480829558 } } }, "workers": { "total": 1.3076308950830935, "count": 98802, "self": 0.0, "children": { "worker_root": { "total": 3234.634878535895, "count": 98802, "is_parallel": true, "self": 1310.5118610349505, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002046505000180332, "count": 1, "is_parallel": true, "self": 0.0007026930002211884, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013438119999591436, "count": 8, "is_parallel": true, "self": 0.0013438119999591436 } } }, "UnityEnvironment.step": { "total": 0.048559485000168934, "count": 1, "is_parallel": true, "self": 0.000562087000162137, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048583099987808964, "count": 1, "is_parallel": true, "self": 0.00048583099987808964 }, "communicator.exchange": { "total": 0.045812131999809935, "count": 1, "is_parallel": true, "self": 0.045812131999809935 }, "steps_from_proto": { "total": 0.001699435000318772, "count": 1, "is_parallel": true, "self": 0.00035413400109973736, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013453009992190346, "count": 8, "is_parallel": true, "self": 0.0013453009992190346 } } } } } } }, "UnityEnvironment.step": { "total": 1924.1230175009446, "count": 98801, "is_parallel": true, "self": 50.13635651180812, "children": { "UnityEnvironment._generate_step_input": { "total": 34.76039412415366, "count": 98801, "is_parallel": true, "self": 34.76039412415366 }, "communicator.exchange": { "total": 1685.4522155651202, "count": 98801, "is_parallel": true, "self": 1685.4522155651202 }, "steps_from_proto": { "total": 153.77405129986255, "count": 98801, "is_parallel": true, "self": 31.61574687050779, "children": { "_process_rank_one_or_two_observation": { "total": 122.15830442935476, "count": 790408, "is_parallel": true, "self": 122.15830442935476 } } } } } } } } } } }, "trainer_advance": { "total": 913.138841664068, "count": 98802, "self": 4.366481840794222, "children": { "process_trajectory": { "total": 168.1383491062602, "count": 98802, "self": 167.88175250926042, "children": { "RLTrainer._checkpoint": { "total": 0.25659659699977055, "count": 3, "self": 0.25659659699977055 } } }, "_update_policy": { "total": 740.6340107170136, "count": 707, "self": 391.82401173107564, "children": { "TorchPPOOptimizer.update": { "total": 348.8099989859379, "count": 35019, "self": 348.8099989859379 } } } } }, "trainer_threads": { "total": 1.2749997040373273e-06, "count": 1, "self": 1.2749997040373273e-06 }, "TrainerController._save_models": { "total": 0.1220569279994379, "count": 1, "self": 0.0012719009991997154, "children": { "RLTrainer._checkpoint": { "total": 0.12078502700023819, "count": 1, "self": 0.12078502700023819 } } } } } } } } }