{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.18825048208236694, "min": 0.1878778040409088, "max": 1.425301194190979, "count": 59 }, "Pyramids.Policy.Entropy.sum": { "value": 5659.5625, "min": 5659.5625, "max": 43237.9375, "count": 59 }, "Pyramids.Step.mean": { "value": 1769969.0, "min": 29952.0, "max": 1769969.0, "count": 59 }, "Pyramids.Step.sum": { "value": 1769969.0, "min": 29952.0, "max": 1769969.0, "count": 59 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7749135494232178, "min": -0.09966930747032166, "max": 0.8152589201927185, "count": 59 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 234.02389526367188, "min": -24.02030372619629, "max": 248.99630737304688, "count": 59 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.023779723793268204, "min": -0.016630051657557487, "max": 0.5332277417182922, "count": 59 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.181476593017578, "min": -4.706304550170898, "max": 127.97465515136719, "count": 59 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06828614841009874, "min": 0.06600571331068814, "max": 0.0736672068571953, "count": 59 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.024292226151481, "min": 0.49543908808812576, "max": 1.0762632650666624, "count": 59 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015486014820178787, "min": 0.0009118903933568912, "max": 0.016017079850684644, "count": 59 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23229022230268181, "min": 0.011520164661190905, "max": 0.24025619776026966, "count": 59 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00012449586516806443, "min": 0.00012449586516806443, "max": 0.00029838354339596195, "count": 59 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0018674379775209665, "min": 0.0017857074047644664, "max": 0.0038852439049187337, "count": 59 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.14149860222222224, "min": 0.14149860222222224, "max": 0.19946118095238097, "count": 59 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.1224790333333337, "min": 1.3897045333333333, "max": 2.7675281000000003, "count": 59 }, "Pyramids.Policy.Beta.mean": { "value": 0.004155710362, "min": 0.004155710362, "max": 0.009946171977142856, "count": 59 }, "Pyramids.Policy.Beta.sum": { "value": 0.062335655430000005, "min": 0.059604029780000005, "max": 0.12951861854000002, "count": 59 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011893498711287975, "min": 0.011381366290152073, "max": 0.6019126772880554, "count": 59 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17840248346328735, "min": 0.15933912992477417, "max": 4.213388919830322, "count": 59 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 234.98461538461538, "min": 216.82575757575756, "max": 999.0, "count": 59 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30548.0, "min": 15984.0, "max": 32974.0, "count": 59 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7650153656418508, "min": -1.0000000521540642, "max": 1.7650153656418508, "count": 59 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 229.4519975334406, "min": -32.000001668930054, "max": 233.01019833236933, "count": 59 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7650153656418508, "min": -1.0000000521540642, "max": 1.7650153656418508, "count": 59 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 229.4519975334406, "min": -32.000001668930054, "max": 233.01019833236933, "count": 59 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02878700135132441, "min": 0.02770943201966632, "max": 11.920114131644368, "count": 59 }, "Pyramids.Policy.RndReward.sum": { "value": 3.7423101756721735, "min": 3.4797976894769818, "max": 190.7218261063099, "count": 59 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 59 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 59 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1756656432", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/envs/py310/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": "1756660845" }, "total": 4412.676785355001, "count": 1, "self": 0.5959866470011548, "children": { "run_training.setup": { "total": 0.02195857900005649, "count": 1, "self": 0.02195857900005649 }, "TrainerController.start_learning": { "total": 4412.058840129, "count": 1, "self": 2.8223829529761133, "children": { "TrainerController._reset_env": { "total": 3.11120238400008, "count": 1, "self": 3.11120238400008 }, "TrainerController.advance": { "total": 4405.924639826023, "count": 115011, "self": 2.747035195033277, "children": { "env_step": { "total": 3205.3247321660624, "count": 115011, "self": 2917.2826470810946, "children": { "SubprocessEnvManager._take_step": { "total": 286.2967471729562, "count": 115011, "self": 8.775771924968808, "children": { "TorchPolicy.evaluate": { "total": 277.5209752479874, "count": 111183, "self": 277.5209752479874 } } }, "workers": { "total": 1.7453379120115642, "count": 115011, "self": 0.0, "children": { "worker_root": { "total": 4400.772211166922, "count": 115011, "is_parallel": true, "self": 1708.4380294558218, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0055586049999192255, "count": 1, "is_parallel": true, "self": 0.004088063999915903, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014705410000033226, "count": 8, "is_parallel": true, "self": 0.0014705410000033226 } } }, "UnityEnvironment.step": { "total": 0.053942301999995834, "count": 1, "is_parallel": true, "self": 0.0005691779999779101, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043286300001454947, "count": 1, "is_parallel": true, "self": 0.00043286300001454947 }, "communicator.exchange": { "total": 0.05127877899997202, "count": 1, "is_parallel": true, "self": 0.05127877899997202 }, "steps_from_proto": { "total": 0.0016614820000313557, "count": 1, "is_parallel": true, "self": 0.0003748780001160412, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012866039999153145, "count": 8, "is_parallel": true, "self": 0.0012866039999153145 } } } } } } }, "UnityEnvironment.step": { "total": 2692.3341817111, "count": 115010, "is_parallel": true, "self": 60.84937674008734, "children": { "UnityEnvironment._generate_step_input": { "total": 42.12857882897299, "count": 115010, "is_parallel": true, "self": 42.12857882897299 }, "communicator.exchange": { "total": 2406.9321646100398, "count": 115010, "is_parallel": true, "self": 2406.9321646100398 }, "steps_from_proto": { "total": 182.42406153200022, "count": 115010, "is_parallel": true, "self": 37.77174858468243, "children": { "_process_rank_one_or_two_observation": { "total": 144.6523129473178, "count": 920080, "is_parallel": true, "self": 144.6523129473178 } } } } } } } } } } }, "trainer_advance": { "total": 1197.8528724649273, "count": 115011, "self": 5.453963073963678, "children": { "process_trajectory": { "total": 234.46309701496955, "count": 115011, "self": 234.10938767496907, "children": { "RLTrainer._checkpoint": { "total": 0.3537093400004778, "count": 3, "self": 0.3537093400004778 } } }, "_update_policy": { "total": 957.9358123759941, "count": 816, "self": 534.309010364062, "children": { "TorchPPOOptimizer.update": { "total": 423.6268020119321, "count": 40493, "self": 423.6268020119321 } } } } } } }, "trainer_threads": { "total": 1.1299998732283711e-06, "count": 1, "self": 1.1299998732283711e-06 }, "TrainerController._save_models": { "total": 0.20061383600022964, "count": 1, "self": 0.008708407000085572, "children": { "RLTrainer._checkpoint": { "total": 0.19190542900014407, "count": 1, "self": 0.19190542900014407 } } } } } } }