{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4851890504360199, "min": 0.4738651216030121, "max": 1.4200611114501953, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14602.25, "min": 14200.7900390625, "max": 43078.97265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989930.0, "min": 29971.0, "max": 989930.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989930.0, "min": 29971.0, "max": 989930.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3410188555717468, "min": -0.0897306278347969, "max": 0.35677194595336914, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 90.02897644042969, "min": -21.804542541503906, "max": 94.18778991699219, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0012974436394870281, "min": -0.0033821710385382175, "max": 0.46434852480888367, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.3425251245498657, "min": -0.8793644905090332, "max": 110.51494598388672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0677137653928228, "min": 0.06656944238610438, "max": 0.07526195281007816, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9479927154995191, "min": 0.605810363217116, "max": 1.0536673393410942, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012445013703698006, "min": 0.0006729796774595343, "max": 0.012445013703698006, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17423019185177208, "min": 0.008748735806973947, "max": 0.17423019185177208, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3698546862714305e-06, "min": 7.3698546862714305e-06, "max": 0.0002949325350224889, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010317796560780002, "min": 0.00010317796560780002, "max": 0.0037575910474697003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245658571428572, "min": 0.10245658571428572, "max": 0.19831084444444447, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343922, "min": 1.4343922, "max": 2.6525303, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002554129128571429, "min": 0.0002554129128571429, "max": 0.00983125336, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003575780780000001, "min": 0.003575780780000001, "max": 0.12526777697, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010136074386537075, "min": 0.010136074386537075, "max": 0.49468284845352173, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1419050395488739, "min": 0.1419050395488739, "max": 4.452145576477051, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 503.44262295081967, "min": 470.31666666666666, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30710.0, "min": 16769.0, "max": 33171.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2669704721355048, "min": -0.9998581159499383, "max": 1.3629633077730736, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 77.28519880026579, "min": -30.99560159444809, "max": 81.77779846638441, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2669704721355048, "min": -0.9998581159499383, "max": 1.3629633077730736, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 77.28519880026579, "min": -30.99560159444809, "max": 81.77779846638441, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05247215958184288, "min": 0.05161820470336049, "max": 10.493693926268154, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2008017344924156, "min": 3.097092282201629, "max": 188.88649067282677, "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": "1738602626", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1738605010" }, "total": 2384.071341423, "count": 1, "self": 0.4764068380000026, "children": { "run_training.setup": { "total": 0.020855919000041467, "count": 1, "self": 0.020855919000041467 }, "TrainerController.start_learning": { "total": 2383.574078666, "count": 1, "self": 1.4139266411498284, "children": { "TrainerController._reset_env": { "total": 2.3541655149997496, "count": 1, "self": 2.3541655149997496 }, "TrainerController.advance": { "total": 2379.70231460785, "count": 63487, "self": 1.3679987978184727, "children": { "env_step": { "total": 1628.945394239015, "count": 63487, "self": 1469.591929730047, "children": { "SubprocessEnvManager._take_step": { "total": 158.5246442699122, "count": 63487, "self": 4.8476766159878935, "children": { "TorchPolicy.evaluate": { "total": 153.6769676539243, "count": 62539, "self": 153.6769676539243 } } }, "workers": { "total": 0.8288202390558581, "count": 63487, "self": 0.0, "children": { "worker_root": { "total": 2378.236928909006, "count": 63487, "is_parallel": true, "self": 1027.2644158099415, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021465299996634712, "count": 1, "is_parallel": true, "self": 0.0007103909988472878, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014361390008161834, "count": 8, "is_parallel": true, "self": 0.0014361390008161834 } } }, "UnityEnvironment.step": { "total": 0.05045716199992967, "count": 1, "is_parallel": true, "self": 0.0005671649996656924, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006301020002865698, "count": 1, "is_parallel": true, "self": 0.0006301020002865698 }, "communicator.exchange": { "total": 0.04743878499994025, "count": 1, "is_parallel": true, "self": 0.04743878499994025 }, "steps_from_proto": { "total": 0.0018211100000371516, "count": 1, "is_parallel": true, "self": 0.0003976779998993152, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014234320001378364, "count": 8, "is_parallel": true, "self": 0.0014234320001378364 } } } } } } }, "UnityEnvironment.step": { "total": 1350.9725130990646, "count": 63486, "is_parallel": true, "self": 33.379725546039936, "children": { "UnityEnvironment._generate_step_input": { "total": 23.62005600610928, "count": 63486, "is_parallel": true, "self": 23.62005600610928 }, "communicator.exchange": { "total": 1194.08883758102, "count": 63486, "is_parallel": true, "self": 1194.08883758102 }, "steps_from_proto": { "total": 99.88389396589537, "count": 63486, "is_parallel": true, "self": 19.652364975014734, "children": { "_process_rank_one_or_two_observation": { "total": 80.23152899088063, "count": 507888, "is_parallel": true, "self": 80.23152899088063 } } } } } } } } } } }, "trainer_advance": { "total": 749.3889215710165, "count": 63487, "self": 2.753512451999086, "children": { "process_trajectory": { "total": 138.936428137019, "count": 63487, "self": 138.6536137700191, "children": { "RLTrainer._checkpoint": { "total": 0.2828143669999008, "count": 2, "self": 0.2828143669999008 } } }, "_update_policy": { "total": 607.6989809819984, "count": 462, "self": 339.369786689937, "children": { "TorchPPOOptimizer.update": { "total": 268.3291942920614, "count": 22752, "self": 268.3291942920614 } } } } } } }, "trainer_threads": { "total": 9.490004231338389e-07, "count": 1, "self": 9.490004231338389e-07 }, "TrainerController._save_models": { "total": 0.1036709529998916, "count": 1, "self": 0.0018145940002796124, "children": { "RLTrainer._checkpoint": { "total": 0.10185635899961198, "count": 1, "self": 0.10185635899961198 } } } } } } }