{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39507654309272766, "min": 0.39507654309272766, "max": 1.470383882522583, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11921.830078125, "min": 11921.830078125, "max": 44605.56640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989922.0, "min": 29952.0, "max": 989922.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989922.0, "min": 29952.0, "max": 989922.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4461936354637146, "min": -0.2279430329799652, "max": 0.5160892605781555, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 118.2413101196289, "min": -54.022499084472656, "max": 142.44064331054688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.636345386505127, "min": -0.636345386505127, "max": 0.37769776582717896, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -168.63153076171875, "min": -168.63153076171875, "max": 90.6474609375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06850698943543693, "min": 0.06539290678270121, "max": 0.07272253233116187, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.959097852096117, "min": 0.4817852897438403, "max": 1.0722308598245338, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.05238519665657631, "min": 0.0011203116768338823, "max": 0.05238519665657631, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.7333927531920683, "min": 0.013443740122006586, "max": 0.7333927531920683, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.722975997135712e-06, "min": 7.722975997135712e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010812166395989998, "min": 0.00010812166395989998, "max": 0.003372681175773, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257429285714284, "min": 0.10257429285714284, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360400999999998, "min": 1.3886848, "max": 2.4860058, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002671718564285714, "min": 0.0002671718564285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00374040599, "min": 0.00374040599, "max": 0.1124402773, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011850998736917973, "min": 0.01156744547188282, "max": 0.5448733568191528, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16591398417949677, "min": 0.16194424033164978, "max": 3.8141133785247803, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 401.375, "min": 370.17721518987344, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28899.0, "min": 15984.0, "max": 32536.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4319055332905717, "min": -1.0000000521540642, "max": 1.6164499761536717, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 103.09719839692116, "min": -30.567401699721813, "max": 129.31599809229374, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4319055332905717, "min": -1.0000000521540642, "max": 1.6164499761536717, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 103.09719839692116, "min": -30.567401699721813, "max": 129.31599809229374, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04968863722671005, "min": 0.048258321235022904, "max": 11.16299851424992, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.577581880323123, "min": 3.3780824864516035, "max": 178.60797622799873, "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": "1786974541", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [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": "1786976860" }, "total": 2318.968575935, "count": 1, "self": 0.4846778920000361, "children": { "run_training.setup": { "total": 0.03824786599989238, "count": 1, "self": 0.03824786599989238 }, "TrainerController.start_learning": { "total": 2318.445650177, "count": 1, "self": 1.4247627170584565, "children": { "TrainerController._reset_env": { "total": 2.7901375179999377, "count": 1, "self": 2.7901375179999377 }, "TrainerController.advance": { "total": 2314.157909300942, "count": 63834, "self": 1.4519754669167924, "children": { "env_step": { "total": 1689.33989015398, "count": 63834, "self": 1534.9520266308805, "children": { "SubprocessEnvManager._take_step": { "total": 153.5883198820311, "count": 63834, "self": 4.7144009359581105, "children": { "TorchPolicy.evaluate": { "total": 148.873918946073, "count": 62548, "self": 148.873918946073 } } }, "workers": { "total": 0.7995436410683396, "count": 63834, "self": 0.0, "children": { "worker_root": { "total": 2312.462014566981, "count": 63834, "is_parallel": true, "self": 896.4887691780236, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004348642999957519, "count": 1, "is_parallel": true, "self": 0.0022412930002246867, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021073499997328327, "count": 8, "is_parallel": true, "self": 0.0021073499997328327 } } }, "UnityEnvironment.step": { "total": 0.05089235000014014, "count": 1, "is_parallel": true, "self": 0.000609070000336942, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004952239996782737, "count": 1, "is_parallel": true, "self": 0.0004952239996782737 }, "communicator.exchange": { "total": 0.04774054400013483, "count": 1, "is_parallel": true, "self": 0.04774054400013483 }, "steps_from_proto": { "total": 0.0020475119999900926, "count": 1, "is_parallel": true, "self": 0.00034739300008368446, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017001189999064081, "count": 8, "is_parallel": true, "self": 0.0017001189999064081 } } } } } } }, "UnityEnvironment.step": { "total": 1415.9732453889574, "count": 63833, "is_parallel": true, "self": 35.011682742883295, "children": { "UnityEnvironment._generate_step_input": { "total": 23.655111745050817, "count": 63833, "is_parallel": true, "self": 23.655111745050817 }, "communicator.exchange": { "total": 1246.2953057760142, "count": 63833, "is_parallel": true, "self": 1246.2953057760142 }, "steps_from_proto": { "total": 111.01114512500908, "count": 63833, "is_parallel": true, "self": 23.406139230038207, "children": { "_process_rank_one_or_two_observation": { "total": 87.60500589497087, "count": 510664, "is_parallel": true, "self": 87.60500589497087 } } } } } } } } } } }, "trainer_advance": { "total": 623.3660436800451, "count": 63834, "self": 2.675167473013971, "children": { "process_trajectory": { "total": 111.4088839050305, "count": 63834, "self": 111.23089292603117, "children": { "RLTrainer._checkpoint": { "total": 0.17799097899933258, "count": 2, "self": 0.17799097899933258 } } }, "_update_policy": { "total": 509.2819923020006, "count": 452, "self": 272.1819744640161, "children": { "TorchPPOOptimizer.update": { "total": 237.10001783798452, "count": 22776, "self": 237.10001783798452 } } } } } } }, "trainer_threads": { "total": 1.1860001905006357e-06, "count": 1, "self": 1.1860001905006357e-06 }, "TrainerController._save_models": { "total": 0.07283945499966649, "count": 1, "self": 0.0009941919997800142, "children": { "RLTrainer._checkpoint": { "total": 0.07184526299988647, "count": 1, "self": 0.07184526299988647 } } } } } } }