{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.40212440490722656, "min": 0.36709073185920715, "max": 1.4265342950820923, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11902.8828125, "min": 11059.7099609375, "max": 43275.34375, "count": 33 }, "Pyramids.Step.mean": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5630162358283997, "min": -0.08861038088798523, "max": 0.5832198858261108, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 157.64454650878906, "min": -21.3551025390625, "max": 158.63580322265625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02641119621694088, "min": -0.004610844422131777, "max": 0.4494186043739319, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.395134925842285, "min": -1.244928002357483, "max": 106.51220703125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06895791633550764, "min": 0.06666209785301665, "max": 0.07443510824196976, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9654108286971069, "min": 0.5115861577898781, "max": 1.0670551488726108, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016325661871330034, "min": 0.0005195647160374083, "max": 0.016325661871330034, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2285592661986205, "min": 0.0072739060245237165, "max": 0.2285592661986205, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.500097500000003e-06, "min": 7.500097500000003e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010500136500000004, "min": 0.00010500136500000004, "max": 0.0035080892306369998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025, "min": 0.1025, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349999999999998, "min": 1.3886848, "max": 2.5724134999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002597500000000001, "min": 0.0002597500000000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036365000000000013, "min": 0.0036365000000000013, "max": 0.11695936369999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014370889402925968, "min": 0.012685737572610378, "max": 0.4996093809604645, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2011924535036087, "min": 0.17760032415390015, "max": 3.497265577316284, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 336.97802197802196, "min": 325.2325581395349, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30665.0, "min": 15984.0, "max": 34135.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6190549297319663, "min": -1.0000000521540642, "max": 1.6343259106815597, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 147.33399860560894, "min": -30.690001651644707, "max": 147.33399860560894, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6190549297319663, "min": -1.0000000521540642, "max": 1.6343259106815597, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 147.33399860560894, "min": -30.690001651644707, "max": 147.33399860560894, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05010853482195711, "min": 0.04977075264846635, "max": 9.813911650329828, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.559876668798097, "min": 3.9318894592288416, "max": 157.02258640527725, "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": "1721829101", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1721831476" }, "total": 2374.7568269250005, "count": 1, "self": 0.4767522310003187, "children": { "run_training.setup": { "total": 0.051235320000159845, "count": 1, "self": 0.051235320000159845 }, "TrainerController.start_learning": { "total": 2374.228839374, "count": 1, "self": 1.5783103899889284, "children": { "TrainerController._reset_env": { "total": 2.0833932470000036, "count": 1, "self": 2.0833932470000036 }, "TrainerController.advance": { "total": 2370.467860519011, "count": 63674, "self": 1.7027735611745811, "children": { "env_step": { "total": 1713.3201718489076, "count": 63674, "self": 1568.3114534518131, "children": { "SubprocessEnvManager._take_step": { "total": 144.0697607540369, "count": 63674, "self": 5.162417979031034, "children": { "TorchPolicy.evaluate": { "total": 138.90734277500587, "count": 62549, "self": 138.90734277500587 } } }, "workers": { "total": 0.9389576430576199, "count": 63674, "self": 0.0, "children": { "worker_root": { "total": 2368.4729767190443, "count": 63674, "is_parallel": true, "self": 935.5674318960914, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022678339996673458, "count": 1, "is_parallel": true, "self": 0.0006671639994237921, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016006700002435537, "count": 8, "is_parallel": true, "self": 0.0016006700002435537 } } }, "UnityEnvironment.step": { "total": 0.049275236999619665, "count": 1, "is_parallel": true, "self": 0.0006504169996333076, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004741180000564782, "count": 1, "is_parallel": true, "self": 0.0004741180000564782 }, "communicator.exchange": { "total": 0.04638106699985656, "count": 1, "is_parallel": true, "self": 0.04638106699985656 }, "steps_from_proto": { "total": 0.0017696350000733219, "count": 1, "is_parallel": true, "self": 0.0003893460002473148, "children": { "_process_rank_one_or_two_observation": { "total": 0.001380288999826007, "count": 8, "is_parallel": true, "self": 0.001380288999826007 } } } } } } }, "UnityEnvironment.step": { "total": 1432.9055448229528, "count": 63673, "is_parallel": true, "self": 35.64477297083886, "children": { "UnityEnvironment._generate_step_input": { "total": 24.80710887608211, "count": 63673, "is_parallel": true, "self": 24.80710887608211 }, "communicator.exchange": { "total": 1267.6219799939608, "count": 63673, "is_parallel": true, "self": 1267.6219799939608 }, "steps_from_proto": { "total": 104.83168298207102, "count": 63673, "is_parallel": true, "self": 22.088762846435657, "children": { "_process_rank_one_or_two_observation": { "total": 82.74292013563536, "count": 509384, "is_parallel": true, "self": 82.74292013563536 } } } } } } } } } } }, "trainer_advance": { "total": 655.4449151089289, "count": 63674, "self": 2.9623594679196685, "children": { "process_trajectory": { "total": 135.56380608100244, "count": 63674, "self": 135.35418586000287, "children": { "RLTrainer._checkpoint": { "total": 0.20962022099956812, "count": 2, "self": 0.20962022099956812 } } }, "_update_policy": { "total": 516.9187495600067, "count": 449, "self": 307.0843011319689, "children": { "TorchPPOOptimizer.update": { "total": 209.83444842803783, "count": 22803, "self": 209.83444842803783 } } } } } } }, "trainer_threads": { "total": 1.8330001694266684e-06, "count": 1, "self": 1.8330001694266684e-06 }, "TrainerController._save_models": { "total": 0.09927338499983307, "count": 1, "self": 0.0014446470004259027, "children": { "RLTrainer._checkpoint": { "total": 0.09782873799940717, "count": 1, "self": 0.09782873799940717 } } } } } } }