{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5660998821258545, "min": 0.5660998821258545, "max": 1.428710699081421, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16946.765625, "min": 16946.765625, "max": 43341.3671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989900.0, "min": 29952.0, "max": 989900.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989900.0, "min": 29952.0, "max": 989900.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4764350354671478, "min": -0.17962731420993805, "max": 0.5362585186958313, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.1138916015625, "min": -42.57167434692383, "max": 146.93482971191406, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011451523751020432, "min": -0.03512711077928543, "max": 0.32457488775253296, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.103363037109375, "min": -9.133049011230469, "max": 78.22254943847656, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07165076531029105, "min": 0.06538580496441336, "max": 0.07396303245214883, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0031107143440747, "min": 0.5034955142252548, "max": 1.0792164304681742, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015795160233600263, "min": 0.000623763573245748, "max": 0.017329472846107648, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2211322432704037, "min": 0.008732690025440472, "max": 0.24261261984550705, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.668654586671425e-06, "min": 7.668654586671425e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010736116421339996, "min": 0.00010736116421339996, "max": 0.0035079581306806996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255618571428572, "min": 0.10255618571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357866000000001, "min": 1.3886848, "max": 2.5693193, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002653629528571428, "min": 0.0002653629528571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003715081339999999, "min": 0.003715081339999999, "max": 0.11695499807000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014349530450999737, "min": 0.014349530450999737, "max": 0.5073192119598389, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20089343190193176, "min": 0.20089343190193176, "max": 3.551234483718872, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 377.9620253164557, "min": 333.64367816091954, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29859.0, "min": 15984.0, "max": 33029.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5713873250009138, "min": -1.0000000521540642, "max": 1.592829711634565, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 124.1395986750722, "min": -30.318201646208763, "max": 139.97239822149277, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5713873250009138, "min": -1.0000000521540642, "max": 1.592829711634565, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 124.1395986750722, "min": -30.318201646208763, "max": 139.97239822149277, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05639404855772434, "min": 0.05210138431721134, "max": 9.95637315697968, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.455129836060223, "min": 3.926524431386497, "max": 159.30197051167488, "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": "1703846062", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703848360" }, "total": 2297.6365803090002, "count": 1, "self": 0.4962553610002942, "children": { "run_training.setup": { "total": 0.05123457000001963, "count": 1, "self": 0.05123457000001963 }, "TrainerController.start_learning": { "total": 2297.089090378, "count": 1, "self": 1.5413659199543872, "children": { "TrainerController._reset_env": { "total": 3.120088877999933, "count": 1, "self": 3.120088877999933 }, "TrainerController.advance": { "total": 2292.339907224046, "count": 63673, "self": 1.5789310290547292, "children": { "env_step": { "total": 1651.0787952479782, "count": 63673, "self": 1510.6293528338356, "children": { "SubprocessEnvManager._take_step": { "total": 139.52243830603913, "count": 63673, "self": 5.000692533045367, "children": { "TorchPolicy.evaluate": { "total": 134.52174577299377, "count": 62566, "self": 134.52174577299377 } } }, "workers": { "total": 0.9270041081034606, "count": 63673, "self": 0.0, "children": { "worker_root": { "total": 2291.600198806984, "count": 63673, "is_parallel": true, "self": 910.035566477975, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0048255630000539895, "count": 1, "is_parallel": true, "self": 0.0034598599999071666, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013657030001468229, "count": 8, "is_parallel": true, "self": 0.0013657030001468229 } } }, "UnityEnvironment.step": { "total": 0.05230988699997852, "count": 1, "is_parallel": true, "self": 0.0006373999998459112, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004912440000452989, "count": 1, "is_parallel": true, "self": 0.0004912440000452989 }, "communicator.exchange": { "total": 0.04934031100003722, "count": 1, "is_parallel": true, "self": 0.04934031100003722 }, "steps_from_proto": { "total": 0.0018409320000500884, "count": 1, "is_parallel": true, "self": 0.00039377000018703257, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014471619998630558, "count": 8, "is_parallel": true, "self": 0.0014471619998630558 } } } } } } }, "UnityEnvironment.step": { "total": 1381.5646323290089, "count": 63672, "is_parallel": true, "self": 37.1788479359559, "children": { "UnityEnvironment._generate_step_input": { "total": 26.09288680104146, "count": 63672, "is_parallel": true, "self": 26.09288680104146 }, "communicator.exchange": { "total": 1211.3676374890154, "count": 63672, "is_parallel": true, "self": 1211.3676374890154 }, "steps_from_proto": { "total": 106.92526010299616, "count": 63672, "is_parallel": true, "self": 22.035456321103652, "children": { "_process_rank_one_or_two_observation": { "total": 84.88980378189251, "count": 509376, "is_parallel": true, "self": 84.88980378189251 } } } } } } } } } } }, "trainer_advance": { "total": 639.6821809470129, "count": 63673, "self": 2.948825311088285, "children": { "process_trajectory": { "total": 132.8290684359265, "count": 63673, "self": 132.6258008769264, "children": { "RLTrainer._checkpoint": { "total": 0.2032675590000963, "count": 2, "self": 0.2032675590000963 } } }, "_update_policy": { "total": 503.90428719999807, "count": 451, "self": 298.17178962899163, "children": { "TorchPPOOptimizer.update": { "total": 205.73249757100643, "count": 22782, "self": 205.73249757100643 } } } } } } }, "trainer_threads": { "total": 1.2509999578469433e-06, "count": 1, "self": 1.2509999578469433e-06 }, "TrainerController._save_models": { "total": 0.08772710499988534, "count": 1, "self": 0.0014046089995645161, "children": { "RLTrainer._checkpoint": { "total": 0.08632249600032083, "count": 1, "self": 0.08632249600032083 } } } } } } }