{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4974146783351898, "min": 0.46742406487464905, "max": 1.496902346611023, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14898.564453125, "min": 13925.498046875, "max": 45410.03125, "count": 33 }, "Pyramids.Step.mean": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4042978286743164, "min": -0.10191190242767334, "max": 0.45109280943870544, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 110.37330627441406, "min": -24.560768127441406, "max": 120.44178009033203, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06810474395751953, "min": -0.03129679709672928, "max": 0.30708253383636475, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 18.592594146728516, "min": -7.9493865966796875, "max": 74.31397247314453, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0663178983723767, "min": 0.06520124614083518, "max": 0.07302835883079593, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9284505772132738, "min": 0.5056778671130961, "max": 1.0303814954457657, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017021256550617096, "min": 0.0008146566462248917, "max": 0.017021256550617096, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23829759170863932, "min": 0.011405193047148484, "max": 0.23829759170863932, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.568840334228572e-06, "min": 7.568840334228572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010596376467920001, "min": 0.00010596376467920001, "max": 0.0036333166888944998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252291428571429, "min": 0.10252291428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353208000000002, "min": 1.3886848, "max": 2.6111055000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026203913714285717, "min": 0.00026203913714285717, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00366854792, "min": 0.00366854792, "max": 0.12112943945000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013958967290818691, "min": 0.013958967290818691, "max": 0.49822303652763367, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19542554020881653, "min": 0.19542554020881653, "max": 3.4875612258911133, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 430.65277777777777, "min": 421.6857142857143, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31007.0, "min": 15984.0, "max": 33554.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4582027554925945, "min": -1.0000000521540642, "max": 1.521159974166325, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 104.9905983954668, "min": -28.597001545131207, "max": 106.48119819164276, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4582027554925945, "min": -1.0000000521540642, "max": 1.521159974166325, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 104.9905983954668, "min": -28.597001545131207, "max": 106.48119819164276, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06229965716597184, "min": 0.06169865586603659, "max": 10.574366303160787, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.485575315949973, "min": 4.318905910622561, "max": 169.1898608505726, "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": "1764590669", "python_version": "3.10.6 | packaged by conda-forge | (main, Aug 22 2022, 20:35:26) [GCC 10.4.0]", "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", "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": "1764593027" }, "total": 2357.4462465429997, "count": 1, "self": 0.6822104259990738, "children": { "run_training.setup": { "total": 0.033529772000292724, "count": 1, "self": 0.033529772000292724 }, "TrainerController.start_learning": { "total": 2356.7305063450003, "count": 1, "self": 1.6479185770303957, "children": { "TrainerController._reset_env": { "total": 2.5253059189999476, "count": 1, "self": 2.5253059189999476 }, "TrainerController.advance": { "total": 2352.47396804497, "count": 63562, "self": 1.855875773990192, "children": { "env_step": { "total": 1655.3416131259119, "count": 63562, "self": 1484.8434439579887, "children": { "SubprocessEnvManager._take_step": { "total": 169.43014482714898, "count": 63562, "self": 5.213715154056445, "children": { "TorchPolicy.evaluate": { "total": 164.21642967309253, "count": 62559, "self": 164.21642967309253 } } }, "workers": { "total": 1.0680243407741727, "count": 63562, "self": 0.0, "children": { "worker_root": { "total": 2349.517061511885, "count": 63562, "is_parallel": true, "self": 998.9021128497116, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026042959998449078, "count": 1, "is_parallel": true, "self": 0.0007764569991195458, "children": { "_process_rank_one_or_two_observation": { "total": 0.001827839000725362, "count": 8, "is_parallel": true, "self": 0.001827839000725362 } } }, "UnityEnvironment.step": { "total": 0.050039310999636655, "count": 1, "is_parallel": true, "self": 0.0005490039993674145, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045168199994805036, "count": 1, "is_parallel": true, "self": 0.00045168199994805036 }, "communicator.exchange": { "total": 0.04724044100021274, "count": 1, "is_parallel": true, "self": 0.04724044100021274 }, "steps_from_proto": { "total": 0.0017981840001084493, "count": 1, "is_parallel": true, "self": 0.0004797269984919694, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013184570016164798, "count": 8, "is_parallel": true, "self": 0.0013184570016164798 } } } } } } }, "UnityEnvironment.step": { "total": 1350.6149486621734, "count": 63561, "is_parallel": true, "self": 36.2927346902743, "children": { "UnityEnvironment._generate_step_input": { "total": 23.63818100607932, "count": 63561, "is_parallel": true, "self": 23.63818100607932 }, "communicator.exchange": { "total": 1176.231023491874, "count": 63561, "is_parallel": true, "self": 1176.231023491874 }, "steps_from_proto": { "total": 114.45300947394571, "count": 63561, "is_parallel": true, "self": 25.026604518810927, "children": { "_process_rank_one_or_two_observation": { "total": 89.42640495513479, "count": 508488, "is_parallel": true, "self": 89.42640495513479 } } } } } } } } } } }, "trainer_advance": { "total": 695.2764791450682, "count": 63562, "self": 3.323459063998598, "children": { "process_trajectory": { "total": 134.7056308500596, "count": 63562, "self": 134.51638966705923, "children": { "RLTrainer._checkpoint": { "total": 0.18924118300037662, "count": 2, "self": 0.18924118300037662 } } }, "_update_policy": { "total": 557.24738923101, "count": 453, "self": 308.628019144021, "children": { "TorchPPOOptimizer.update": { "total": 248.61937008698897, "count": 22752, "self": 248.61937008698897 } } } } } } }, "trainer_threads": { "total": 8.850001904647797e-07, "count": 1, "self": 8.850001904647797e-07 }, "TrainerController._save_models": { "total": 0.0833129189995816, "count": 1, "self": 0.0012929419999636593, "children": { "RLTrainer._checkpoint": { "total": 0.08201997699961794, "count": 1, "self": 0.08201997699961794 } } } } } } }