{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35350215435028076, "min": 0.35056886076927185, "max": 1.4119893312454224, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10701.216796875, "min": 10399.2744140625, "max": 42834.109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989997.0, "min": 29914.0, "max": 989997.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989997.0, "min": 29914.0, "max": 989997.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6375001668930054, "min": -0.09322047233581543, "max": 0.6375001668930054, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 182.96255493164062, "min": -22.46613311767578, "max": 182.96255493164062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0072271632961928844, "min": -0.009482596069574356, "max": 0.2322693020105362, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.0741958618164062, "min": -2.664609432220459, "max": 55.280094146728516, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06709204318844166, "min": 0.06528317467226381, "max": 0.07295222917490429, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9392886046381831, "min": 0.6565700625741386, "max": 1.0761380936019123, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01433868105798837, "min": 0.0011014402203348567, "max": 0.018388370004859534, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20074153481183718, "min": 0.012115842423683423, "max": 0.2581796539210094, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.286711856842859e-06, "min": 7.286711856842859e-06, "max": 0.0002948858017047333, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010201396599580002, "min": 0.00010201396599580002, "max": 0.0036350377883207995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242887142857145, "min": 0.10242887142857145, "max": 0.19829526666666666, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340042000000002, "min": 1.4340042000000002, "max": 2.6116791999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002526442557142858, "min": 0.0002526442557142858, "max": 0.009829697140000001, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035370195800000013, "min": 0.0035370195800000013, "max": 0.12118675208, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007857595570385456, "min": 0.007857595570385456, "max": 0.34187182784080505, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11000633984804153, "min": 0.11000633984804153, "max": 3.0768463611602783, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 303.1684210526316, "min": 297.70873786407765, "max": 996.84375, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28801.0, "min": 15818.0, "max": 33751.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6757747207817277, "min": -0.9353000533301383, "max": 1.6757747207817277, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 159.19859847426414, "min": -29.929601706564426, "max": 171.33459842205048, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6757747207817277, "min": -0.9353000533301383, "max": 1.6757747207817277, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 159.19859847426414, "min": -29.929601706564426, "max": 171.33459842205048, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02490549862142009, "min": 0.02490549862142009, "max": 6.5973740008194, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3660223690349085, "min": 2.336575924156932, "max": 105.5579840131104, "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": "1760314757", "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": "1760317018" }, "total": 2260.109618404, "count": 1, "self": 0.5393168809996496, "children": { "run_training.setup": { "total": 0.025295243000073242, "count": 1, "self": 0.025295243000073242 }, "TrainerController.start_learning": { "total": 2259.54500628, "count": 1, "self": 1.3125393200430153, "children": { "TrainerController._reset_env": { "total": 3.0738910759999953, "count": 1, "self": 3.0738910759999953 }, "TrainerController.advance": { "total": 2255.082457193957, "count": 64051, "self": 1.3782071399723463, "children": { "env_step": { "total": 1604.140856491013, "count": 64051, "self": 1461.7296846371269, "children": { "SubprocessEnvManager._take_step": { "total": 141.6340976639084, "count": 64051, "self": 4.350659463879424, "children": { "TorchPolicy.evaluate": { "total": 137.28343820002897, "count": 62576, "self": 137.28343820002897 } } }, "workers": { "total": 0.7770741899778386, "count": 64051, "self": 0.0, "children": { "worker_root": { "total": 2252.659682663048, "count": 64051, "is_parallel": true, "self": 903.3824065290705, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004206995000004099, "count": 1, "is_parallel": true, "self": 0.002987178000125823, "children": { "_process_rank_one_or_two_observation": { "total": 0.001219816999878276, "count": 8, "is_parallel": true, "self": 0.001219816999878276 } } }, "UnityEnvironment.step": { "total": 0.04651009999997768, "count": 1, "is_parallel": true, "self": 0.0005401220000749163, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004402029999255319, "count": 1, "is_parallel": true, "self": 0.0004402029999255319 }, "communicator.exchange": { "total": 0.04396293800004969, "count": 1, "is_parallel": true, "self": 0.04396293800004969 }, "steps_from_proto": { "total": 0.0015668369999275455, "count": 1, "is_parallel": true, "self": 0.00032234600007541303, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012444909998521325, "count": 8, "is_parallel": true, "self": 0.0012444909998521325 } } } } } } }, "UnityEnvironment.step": { "total": 1349.2772761339775, "count": 64050, "is_parallel": true, "self": 33.24914842584076, "children": { "UnityEnvironment._generate_step_input": { "total": 21.862773190066036, "count": 64050, "is_parallel": true, "self": 21.862773190066036 }, "communicator.exchange": { "total": 1192.5072923800499, "count": 64050, "is_parallel": true, "self": 1192.5072923800499 }, "steps_from_proto": { "total": 101.65806213802068, "count": 64050, "is_parallel": true, "self": 21.10911618788532, "children": { "_process_rank_one_or_two_observation": { "total": 80.54894595013536, "count": 512400, "is_parallel": true, "self": 80.54894595013536 } } } } } } } } } } }, "trainer_advance": { "total": 649.5633935629717, "count": 64051, "self": 2.636335822971432, "children": { "process_trajectory": { "total": 121.8909774539976, "count": 64051, "self": 121.66815592099795, "children": { "RLTrainer._checkpoint": { "total": 0.22282153299966012, "count": 2, "self": 0.22282153299966012 } } }, "_update_policy": { "total": 525.0360802860026, "count": 460, "self": 292.2366735819967, "children": { "TorchPPOOptimizer.update": { "total": 232.79940670400595, "count": 22758, "self": 232.79940670400595 } } } } } } }, "trainer_threads": { "total": 9.890000001178123e-07, "count": 1, "self": 9.890000001178123e-07 }, "TrainerController._save_models": { "total": 0.0761177009999301, "count": 1, "self": 0.0009657870000410185, "children": { "RLTrainer._checkpoint": { "total": 0.07515191399988908, "count": 1, "self": 0.07515191399988908 } } } } } } }