{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5421552062034607, "min": 0.5109202861785889, "max": 1.4702211618423462, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16351.400390625, "min": 15384.83203125, "max": 44600.62890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989931.0, "min": 29952.0, "max": 989931.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989931.0, "min": 29952.0, "max": 989931.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1463415026664734, "min": -0.09558987617492676, "max": 0.1810888797044754, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 36.43903350830078, "min": -23.037160873413086, "max": 45.99657440185547, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005960748065263033, "min": -0.012978869490325451, "max": 0.6682460904121399, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.4842262268066406, "min": -3.296632766723633, "max": 158.37432861328125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06806919401503723, "min": 0.06538379723635478, "max": 0.07575467328867416, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9529687162105213, "min": 0.5060772345807463, "max": 1.054861680061246, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.009048821650318204, "min": 0.00015163301405559531, "max": 0.011161741889211926, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.12668350310445486, "min": 0.001971229182722739, "max": 0.15626438644896695, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.774704551321427e-06, "min": 7.774704551321427e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010884586371849998, "min": 0.00010884586371849998, "max": 0.0036333313888895994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10259153571428571, "min": 0.10259153571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4362815, "min": 1.3886848, "max": 2.611110400000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002688944178571428, "min": 0.0002688944178571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037645218499999995, "min": 0.0037645218499999995, "max": 0.12112992896000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0168222077190876, "min": 0.015354647301137447, "max": 0.5618124604225159, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2355109006166458, "min": 0.2149650603532791, "max": 3.932687282562256, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 704.8048780487804, "min": 637.1086956521739, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28897.0, "min": 15984.0, "max": 32751.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.6608926519388105, "min": -1.0000000521540642, "max": 0.9040166370881101, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 27.096598729491234, "min": -31.99320164322853, "max": 43.39279858022928, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.6608926519388105, "min": -1.0000000521540642, "max": 0.9040166370881101, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 27.096598729491234, "min": -31.99320164322853, "max": 43.39279858022928, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.12326012659397703, "min": 0.1069977554216166, "max": 12.098094806075096, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.053665190353058, "min": 4.975830416660756, "max": 193.56951689720154, "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": "1781878676", "python_version": "3.10.11 (main, May 16 2023, 00:28:57) [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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1781881029" }, "total": 2353.6250749910005, "count": 1, "self": 0.5344704550002461, "children": { "run_training.setup": { "total": 0.02381314400008705, "count": 1, "self": 0.02381314400008705 }, "TrainerController.start_learning": { "total": 2353.066791392, "count": 1, "self": 1.4768955798440402, "children": { "TrainerController._reset_env": { "total": 2.216733632999876, "count": 1, "self": 2.216733632999876 }, "TrainerController.advance": { "total": 2349.286795397156, "count": 63365, "self": 1.450732352187515, "children": { "env_step": { "total": 1698.5999840099662, "count": 63365, "self": 1536.7075065429908, "children": { "SubprocessEnvManager._take_step": { "total": 161.0474582819529, "count": 63365, "self": 4.891472954865094, "children": { "TorchPolicy.evaluate": { "total": 156.15598532708782, "count": 62563, "self": 156.15598532708782 } } }, "workers": { "total": 0.8450191850224655, "count": 63365, "self": 0.0, "children": { "worker_root": { "total": 2347.404555083034, "count": 63365, "is_parallel": true, "self": 933.9190591480174, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019775870000557916, "count": 1, "is_parallel": true, "self": 0.000693468999088509, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012841180009672826, "count": 8, "is_parallel": true, "self": 0.0012841180009672826 } } }, "UnityEnvironment.step": { "total": 0.05364939500032051, "count": 1, "is_parallel": true, "self": 0.0005865680004717433, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004667029998017824, "count": 1, "is_parallel": true, "self": 0.0004667029998017824 }, "communicator.exchange": { "total": 0.0508433420000074, "count": 1, "is_parallel": true, "self": 0.0508433420000074 }, "steps_from_proto": { "total": 0.0017527820000395877, "count": 1, "is_parallel": true, "self": 0.00041325099982714164, "children": { "_process_rank_one_or_two_observation": { "total": 0.001339531000212446, "count": 8, "is_parallel": true, "self": 0.001339531000212446 } } } } } } }, "UnityEnvironment.step": { "total": 1413.4854959350168, "count": 63364, "is_parallel": true, "self": 35.20592063989125, "children": { "UnityEnvironment._generate_step_input": { "total": 25.055125791067894, "count": 63364, "is_parallel": true, "self": 25.055125791067894 }, "communicator.exchange": { "total": 1238.0361629739941, "count": 63364, "is_parallel": true, "self": 1238.0361629739941 }, "steps_from_proto": { "total": 115.18828653006358, "count": 63364, "is_parallel": true, "self": 23.549093686811375, "children": { "_process_rank_one_or_two_observation": { "total": 91.6391928432522, "count": 506912, "is_parallel": true, "self": 91.6391928432522 } } } } } } } } } } }, "trainer_advance": { "total": 649.2360790350021, "count": 63365, "self": 2.729695350950351, "children": { "process_trajectory": { "total": 115.21554636805104, "count": 63365, "self": 114.96722944405155, "children": { "RLTrainer._checkpoint": { "total": 0.24831692399948224, "count": 2, "self": 0.24831692399948224 } } }, "_update_policy": { "total": 531.2908373160008, "count": 450, "self": 282.17515017301776, "children": { "TorchPPOOptimizer.update": { "total": 249.115687142983, "count": 22764, "self": 249.115687142983 } } } } } } }, "trainer_threads": { "total": 8.510005500284024e-07, "count": 1, "self": 8.510005500284024e-07 }, "TrainerController._save_models": { "total": 0.08636593099981837, "count": 1, "self": 0.0010633989995767479, "children": { "RLTrainer._checkpoint": { "total": 0.08530253200024163, "count": 1, "self": 0.08530253200024163 } } } } } } }