{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.32627230882644653, "min": 0.310393750667572, "max": 1.4600708484649658, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9709.8642578125, "min": 9212.486328125, "max": 44292.7109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5712558031082153, "min": -0.04444899410009384, "max": 0.6565734148025513, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 160.52288818359375, "min": -10.712207794189453, "max": 188.4365692138672, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04985835775732994, "min": -0.014220662415027618, "max": 0.30632174015045166, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 14.010198593139648, "min": -3.6262688636779785, "max": 73.51721954345703, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06580059672641153, "min": 0.06529236195363208, "max": 0.07207587967457672, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9870089508961729, "min": 0.4868131455869666, "max": 1.072660699253902, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017535264942691555, "min": 0.002190011774054695, "max": 0.018045665456318402, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.26302897414037335, "min": 0.020826573471744558, "max": 0.270684981844776, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.525017491693335e-06, "min": 7.525017491693335e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011287526237540003, "min": 0.00011287526237540003, "max": 0.003757280847573099, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250830666666669, "min": 0.10250830666666669, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376246000000002, "min": 1.3886848, "max": 2.6524269, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026057983600000017, "min": 0.00026057983600000017, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003908697540000002, "min": 0.003908697540000002, "max": 0.12525744731000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010826599784195423, "min": 0.010051325894892216, "max": 0.4678378701210022, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16239899396896362, "min": 0.14071856439113617, "max": 3.27486515045166, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 293.8229166666667, "min": 278.71, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28207.0, "min": 15984.0, "max": 33136.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6835443167035113, "min": -1.0000000521540642, "max": 1.7221088946455776, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 163.3037987202406, "min": -26.99300181120634, "max": 173.93299835920334, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6835443167035113, "min": -1.0000000521540642, "max": 1.7221088946455776, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 163.3037987202406, "min": -26.99300181120634, "max": 173.93299835920334, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03284699922549351, "min": 0.031820773443271694, "max": 9.464617356657982, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1861589248728706, "min": 3.1861589248728706, "max": 151.4338777065277, "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": "1756804276", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1756806542" }, "total": 2265.538490375, "count": 1, "self": 0.7097213980005108, "children": { "run_training.setup": { "total": 0.02161192299990944, "count": 1, "self": 0.02161192299990944 }, "TrainerController.start_learning": { "total": 2264.8071570539996, "count": 1, "self": 1.337865490157128, "children": { "TrainerController._reset_env": { "total": 2.013143256999683, "count": 1, "self": 2.013143256999683 }, "TrainerController.advance": { "total": 2261.342070297843, "count": 64219, "self": 1.321271180756412, "children": { "env_step": { "total": 1610.0700564990575, "count": 64219, "self": 1463.793569982181, "children": { "SubprocessEnvManager._take_step": { "total": 145.48931249898033, "count": 64219, "self": 4.5171162087735865, "children": { "TorchPolicy.evaluate": { "total": 140.97219629020674, "count": 62559, "self": 140.97219629020674 } } }, "workers": { "total": 0.7871740178961772, "count": 64219, "self": 0.0, "children": { "worker_root": { "total": 2259.979646944008, "count": 64219, "is_parallel": true, "self": 907.2696887760949, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017344709995086305, "count": 1, "is_parallel": true, "self": 0.0005573899989030906, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011770810006055399, "count": 8, "is_parallel": true, "self": 0.0011770810006055399 } } }, "UnityEnvironment.step": { "total": 0.04652428699955635, "count": 1, "is_parallel": true, "self": 0.0005137399984960211, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004665710002882406, "count": 1, "is_parallel": true, "self": 0.0004665710002882406 }, "communicator.exchange": { "total": 0.043987576000290574, "count": 1, "is_parallel": true, "self": 0.043987576000290574 }, "steps_from_proto": { "total": 0.001556400000481517, "count": 1, "is_parallel": true, "self": 0.00034161600069637643, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012147839997851406, "count": 8, "is_parallel": true, "self": 0.0012147839997851406 } } } } } } }, "UnityEnvironment.step": { "total": 1352.709958167913, "count": 64218, "is_parallel": true, "self": 31.478607767657195, "children": { "UnityEnvironment._generate_step_input": { "total": 22.712420443089286, "count": 64218, "is_parallel": true, "self": 22.712420443089286 }, "communicator.exchange": { "total": 1202.8050685101434, "count": 64218, "is_parallel": true, "self": 1202.8050685101434 }, "steps_from_proto": { "total": 95.71386144702319, "count": 64218, "is_parallel": true, "self": 18.906401823379383, "children": { "_process_rank_one_or_two_observation": { "total": 76.80745962364381, "count": 513744, "is_parallel": true, "self": 76.80745962364381 } } } } } } } } } } }, "trainer_advance": { "total": 649.9507426180289, "count": 64219, "self": 2.6976431360044444, "children": { "process_trajectory": { "total": 122.98024513103064, "count": 64219, "self": 122.7603045140313, "children": { "RLTrainer._checkpoint": { "total": 0.2199406169993381, "count": 2, "self": 0.2199406169993381 } } }, "_update_policy": { "total": 524.2728543509938, "count": 457, "self": 293.6725083270221, "children": { "TorchPPOOptimizer.update": { "total": 230.60034602397172, "count": 22767, "self": 230.60034602397172 } } } } } } }, "trainer_threads": { "total": 1.2150003385613672e-06, "count": 1, "self": 1.2150003385613672e-06 }, "TrainerController._save_models": { "total": 0.11407679399962944, "count": 1, "self": 0.0016552679990127217, "children": { "RLTrainer._checkpoint": { "total": 0.11242152600061672, "count": 1, "self": 0.11242152600061672 } } } } } } }