{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.14890508353710175, "min": 0.14099137485027313, "max": 1.4651432037353516, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4495.7421875, "min": 4220.927734375, "max": 44446.5859375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999879.0, "min": 29952.0, "max": 2999879.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999879.0, "min": 29952.0, "max": 2999879.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7620491981506348, "min": -0.11561503261327744, "max": 0.8446611166000366, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 224.04246520996094, "min": -27.747608184814453, "max": 252.55368041992188, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04605472460389137, "min": -0.00942927785217762, "max": 0.213605597615242, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 13.540088653564453, "min": -2.7910661697387695, "max": 51.265342712402344, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0652759023799768, "min": 0.06354678132540831, "max": 0.07531412609244524, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.979138535699652, "min": 0.4921250750195976, "max": 1.1022237858252244, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017098153240901106, "min": 0.0008646131126434602, "max": 0.017582910410488865, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2564722986135166, "min": 0.009982368795355233, "max": 0.2564722986135166, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4922995026000009e-06, "min": 1.4922995026000009e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2384492539000014e-05, "min": 2.2384492539000014e-05, "max": 0.0040274668575111, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049740000000001, "min": 0.10049740000000001, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5074610000000002, "min": 1.3897045333333333, "max": 2.8424888999999998, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.969026000000005e-05, "min": 5.969026000000005e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008953539000000007, "min": 0.0008953539000000007, "max": 0.13426464111000003, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00483317393809557, "min": 0.004518811125308275, "max": 0.381413072347641, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07249760627746582, "min": 0.06326335668563843, "max": 2.669891595840454, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 243.1404958677686, "min": 223.18115942028984, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29420.0, "min": 15984.0, "max": 32945.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.724834696443613, "min": -1.0000000521540642, "max": 1.7751764601425213, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 208.70499826967716, "min": -32.000001668930054, "max": 241.4239985793829, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.724834696443613, "min": -1.0000000521540642, "max": 1.7751764601425213, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 208.70499826967716, "min": -32.000001668930054, "max": 241.4239985793829, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.012274142774808114, "min": 0.011055106209739908, "max": 8.724391726776958, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.4851712757517816, "min": 1.365028015745338, "max": 139.59026762843132, "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": "1738696680", "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 Training1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1738707877" }, "total": 11196.417351474, "count": 1, "self": 1.654067176999888, "children": { "run_training.setup": { "total": 0.033985454999992726, "count": 1, "self": 0.033985454999992726 }, "TrainerController.start_learning": { "total": 11194.729298842, "count": 1, "self": 7.746257566244822, "children": { "TrainerController._reset_env": { "total": 2.7588633129998925, "count": 1, "self": 2.7588633129998925 }, "TrainerController.advance": { "total": 11184.065838609753, "count": 194966, "self": 7.997460290000163, "children": { "env_step": { "total": 7775.09238527288, "count": 194966, "self": 7262.913120635713, "children": { "SubprocessEnvManager._take_step": { "total": 508.03668117032726, "count": 194966, "self": 21.882202991255326, "children": { "TorchPolicy.evaluate": { "total": 486.15447817907193, "count": 187568, "self": 486.15447817907193 } } }, "workers": { "total": 4.142583466839596, "count": 194966, "self": 0.0, "children": { "worker_root": { "total": 11169.664561206, "count": 194966, "is_parallel": true, "self": 4456.85897805298, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027327339998919342, "count": 1, "is_parallel": true, "self": 0.0008833760000470647, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018493579998448695, "count": 8, "is_parallel": true, "self": 0.0018493579998448695 } } }, "UnityEnvironment.step": { "total": 0.07457364800006872, "count": 1, "is_parallel": true, "self": 0.0007317030001559033, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008831350000946259, "count": 1, "is_parallel": true, "self": 0.0008831350000946259 }, "communicator.exchange": { "total": 0.07076399699985814, "count": 1, "is_parallel": true, "self": 0.07076399699985814 }, "steps_from_proto": { "total": 0.0021948129999600496, "count": 1, "is_parallel": true, "self": 0.0004123349997371406, "children": { "_process_rank_one_or_two_observation": { "total": 0.001782478000222909, "count": 8, "is_parallel": true, "self": 0.001782478000222909 } } } } } } }, "UnityEnvironment.step": { "total": 6712.80558315302, "count": 194965, "is_parallel": true, "self": 134.78812730039135, "children": { "UnityEnvironment._generate_step_input": { "total": 94.75558238996541, "count": 194965, "is_parallel": true, "self": 94.75558238996541 }, "communicator.exchange": { "total": 6097.59145040803, "count": 194965, "is_parallel": true, "self": 6097.59145040803 }, "steps_from_proto": { "total": 385.6704230546329, "count": 194965, "is_parallel": true, "self": 84.68856245514826, "children": { "_process_rank_one_or_two_observation": { "total": 300.98186059948466, "count": 1559720, "is_parallel": true, "self": 300.98186059948466 } } } } } } } } } } }, "trainer_advance": { "total": 3400.9759930468726, "count": 194966, "self": 14.491403208556221, "children": { "process_trajectory": { "total": 517.9199779672974, "count": 194966, "self": 517.1411655012987, "children": { "RLTrainer._checkpoint": { "total": 0.7788124659987261, "count": 6, "self": 0.7788124659987261 } } }, "_update_policy": { "total": 2868.564611871019, "count": 1397, "self": 1123.213762774882, "children": { "TorchPPOOptimizer.update": { "total": 1745.3508490961372, "count": 68439, "self": 1745.3508490961372 } } } } } } }, "trainer_threads": { "total": 1.3660010154126212e-06, "count": 1, "self": 1.3660010154126212e-06 }, "TrainerController._save_models": { "total": 0.1583379870007775, "count": 1, "self": 0.0035320900005899603, "children": { "RLTrainer._checkpoint": { "total": 0.15480589700018754, "count": 1, "self": 0.15480589700018754 } } } } } } }