{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1786358654499054, "min": 0.1729602813720703, "max": 1.4264922142028809, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5381.94140625, "min": 5188.80859375, "max": 43274.06640625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999895.0, "min": 29952.0, "max": 2999895.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999895.0, "min": 29952.0, "max": 2999895.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.798326849937439, "min": -0.10045436769723892, "max": 0.8261003494262695, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 239.498046875, "min": -24.209503173828125, "max": 247.00399780273438, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004771160893142223, "min": -0.07077280431985855, "max": 0.47514477372169495, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.4313483238220215, "min": -18.825565338134766, "max": 112.60931396484375, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06493475051331485, "min": 0.06355848431814506, "max": 0.07590767054006434, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9090865071864078, "min": 0.5273666315880636, "max": 1.0627073875609008, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016075518079094218, "min": 0.0005911032139517972, "max": 0.01674695685444996, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22505725310731903, "min": 0.00827544499532516, "max": 0.2512043528167494, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.422442383028571e-06, "min": 1.422442383028571e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.9914193362399994e-05, "min": 1.9914193362399994e-05, "max": 0.003969581876806067, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1004741142857143, "min": 0.1004741142857143, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4066376000000003, "min": 1.3962282666666668, "max": 2.7524666666666664, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.736401714285714e-05, "min": 5.736401714285714e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.00080309624, "min": 0.00080309624, "max": 0.13232707394, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005342080723494291, "min": 0.005169548559933901, "max": 0.5847753882408142, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0747891291975975, "min": 0.07237368077039719, "max": 4.093427658081055, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 231.12878787878788, "min": 224.84496124031008, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30509.0, "min": 15984.0, "max": 33172.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7539052460202598, "min": -1.0000000521540642, "max": 1.7751615280142197, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 233.26939772069454, "min": -30.040601700544357, "max": 233.26939772069454, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7539052460202598, "min": -1.0000000521540642, "max": 1.7751615280142197, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 233.26939772069454, "min": -30.040601700544357, "max": 233.26939772069454, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.012777018607369229, "min": 0.012607557796638082, "max": 12.599788771942258, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.6993434747801075, "min": 1.571092986210715, "max": 201.59662035107613, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1721151272", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1721158825" }, "total": 7553.049232601, "count": 1, "self": 0.5439152320004723, "children": { "run_training.setup": { "total": 0.059261960999947405, "count": 1, "self": 0.059261960999947405 }, "TrainerController.start_learning": { "total": 7552.446055408, "count": 1, "self": 4.344209818842501, "children": { "TrainerController._reset_env": { "total": 3.0277392950000603, "count": 1, "self": 3.0277392950000603 }, "TrainerController.advance": { "total": 7544.971828496157, "count": 194814, "self": 4.514263604288317, "children": { "env_step": { "total": 5572.610383709972, "count": 194814, "self": 5158.583673910086, "children": { "SubprocessEnvManager._take_step": { "total": 411.28673787788546, "count": 194814, "self": 14.95557440489722, "children": { "TorchPolicy.evaluate": { "total": 396.33116347298824, "count": 187564, "self": 396.33116347298824 } } }, "workers": { "total": 2.739971922000109, "count": 194814, "self": 0.0, "children": { "worker_root": { "total": 7536.109277617728, "count": 194814, "is_parallel": true, "self": 2772.0221961206926, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007248193999998875, "count": 1, "is_parallel": true, "self": 0.005796612999915851, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014515810000830243, "count": 8, "is_parallel": true, "self": 0.0014515810000830243 } } }, "UnityEnvironment.step": { "total": 0.052252208999902905, "count": 1, "is_parallel": true, "self": 0.0006637289999389395, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045371099997737474, "count": 1, "is_parallel": true, "self": 0.00045371099997737474 }, "communicator.exchange": { "total": 0.049350378999974964, "count": 1, "is_parallel": true, "self": 0.049350378999974964 }, "steps_from_proto": { "total": 0.0017843900000116264, "count": 1, "is_parallel": true, "self": 0.00042422600006375433, "children": { "_process_rank_one_or_two_observation": { "total": 0.001360163999947872, "count": 8, "is_parallel": true, "self": 0.001360163999947872 } } } } } } }, "UnityEnvironment.step": { "total": 4764.087081497036, "count": 194813, "is_parallel": true, "self": 102.83105113299735, "children": { "UnityEnvironment._generate_step_input": { "total": 72.67755063505433, "count": 194813, "is_parallel": true, "self": 72.67755063505433 }, "communicator.exchange": { "total": 4281.532466057943, "count": 194813, "is_parallel": true, "self": 4281.532466057943 }, "steps_from_proto": { "total": 307.04601367104124, "count": 194813, "is_parallel": true, "self": 64.17528828020488, "children": { "_process_rank_one_or_two_observation": { "total": 242.87072539083636, "count": 1558504, "is_parallel": true, "self": 242.87072539083636 } } } } } } } } } } }, "trainer_advance": { "total": 1967.8471811818968, "count": 194814, "self": 8.72232916505709, "children": { "process_trajectory": { "total": 413.36169627185075, "count": 194814, "self": 412.7002595978514, "children": { "RLTrainer._checkpoint": { "total": 0.6614366739993329, "count": 6, "self": 0.6614366739993329 } } }, "_update_policy": { "total": 1545.7631557449888, "count": 1400, "self": 917.5378239409898, "children": { "TorchPPOOptimizer.update": { "total": 628.225331803999, "count": 68373, "self": 628.225331803999 } } } } } } }, "trainer_threads": { "total": 1.2669997886405326e-06, "count": 1, "self": 1.2669997886405326e-06 }, "TrainerController._save_models": { "total": 0.10227653099991585, "count": 1, "self": 0.0016215819996432401, "children": { "RLTrainer._checkpoint": { "total": 0.10065494900027261, "count": 1, "self": 0.10065494900027261 } } } } } } }