{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5698174238204956, "min": 0.5698174238204956, "max": 1.4425628185272217, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17149.224609375, "min": 17149.224609375, "max": 43761.5859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989930.0, "min": 29999.0, "max": 989930.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989930.0, "min": 29999.0, "max": 989930.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.20035213232040405, "min": -0.12577135860919952, "max": 0.25842031836509705, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 50.889442443847656, "min": -30.310895919799805, "max": 66.15560150146484, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.056648217141628265, "min": -0.056648217141628265, "max": 0.42602410912513733, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -14.388647079467773, "min": -14.388647079467773, "max": 101.39373779296875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06754398916936702, "min": 0.06491427004245155, "max": 0.07267964011338161, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9456158483711383, "min": 0.5459778077402202, "max": 1.0439964044809469, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010748632971669957, "min": 0.0007395420238763296, "max": 0.012239639442885251, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1504808616033794, "min": 0.00827360357536779, "max": 0.1713549522003935, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.58381890066429e-06, "min": 7.58381890066429e-06, "max": 0.00029500575166475, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010617346460930006, "min": 0.00010617346460930006, "max": 0.003255975514674899, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252790714285716, "min": 0.10252790714285716, "max": 0.19833524999999996, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353907000000001, "min": 1.4353907000000001, "max": 2.4428687, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002625379235714288, "min": 0.0002625379235714288, "max": 0.009833691475, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036755309300000026, "min": 0.0036755309300000026, "max": 0.10855397749000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014334074221551418, "min": 0.01417706348001957, "max": 0.5550456047058105, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2006770372390747, "min": 0.19847889244556427, "max": 4.440364837646484, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 592.7924528301887, "min": 572.0, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31418.0, "min": 16158.0, "max": 34263.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.7655093976349201, "min": -1.0000000521540642, "max": 1.0866851563806887, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 40.571998074650764, "min": -32.000001668930054, "max": 58.68099844455719, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.7655093976349201, "min": -1.0000000521540642, "max": 1.0866851563806887, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 40.571998074650764, "min": -32.000001668930054, "max": 58.68099844455719, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08756237174452937, "min": 0.08454849987282176, "max": 11.402140800567235, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.640805702460057, "min": 4.3793974336003885, "max": 193.83639360964298, "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": "1742468233", "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": "1742470331" }, "total": 2097.316742059, "count": 1, "self": 0.4756840129994089, "children": { "run_training.setup": { "total": 0.019198450999965644, "count": 1, "self": 0.019198450999965644 }, "TrainerController.start_learning": { "total": 2096.821859595, "count": 1, "self": 1.2852677898504226, "children": { "TrainerController._reset_env": { "total": 2.110498382999822, "count": 1, "self": 2.110498382999822 }, "TrainerController.advance": { "total": 2093.33040271915, "count": 63329, "self": 1.35192169218044, "children": { "env_step": { "total": 1428.9610587799461, "count": 63329, "self": 1280.7124160308645, "children": { "SubprocessEnvManager._take_step": { "total": 147.52215137498683, "count": 63329, "self": 4.530815396937442, "children": { "TorchPolicy.evaluate": { "total": 142.9913359780494, "count": 62570, "self": 142.9913359780494 } } }, "workers": { "total": 0.7264913740948487, "count": 63329, "self": 0.0, "children": { "worker_root": { "total": 2092.4390858220177, "count": 63329, "is_parallel": true, "self": 919.2057557180372, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020065579999481997, "count": 1, "is_parallel": true, "self": 0.0007123699997464428, "children": { "_process_rank_one_or_two_observation": { "total": 0.001294188000201757, "count": 8, "is_parallel": true, "self": 0.001294188000201757 } } }, "UnityEnvironment.step": { "total": 0.053939465999974345, "count": 1, "is_parallel": true, "self": 0.0005187389999719016, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004675499999393651, "count": 1, "is_parallel": true, "self": 0.0004675499999393651 }, "communicator.exchange": { "total": 0.05125669399990329, "count": 1, "is_parallel": true, "self": 0.05125669399990329 }, "steps_from_proto": { "total": 0.0016964830001597875, "count": 1, "is_parallel": true, "self": 0.0003780819999974483, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013184010001623392, "count": 8, "is_parallel": true, "self": 0.0013184010001623392 } } } } } } }, "UnityEnvironment.step": { "total": 1173.2333301039805, "count": 63328, "is_parallel": true, "self": 31.26716715395878, "children": { "UnityEnvironment._generate_step_input": { "total": 22.82900604507313, "count": 63328, "is_parallel": true, "self": 22.82900604507313 }, "communicator.exchange": { "total": 1024.625767373964, "count": 63328, "is_parallel": true, "self": 1024.625767373964 }, "steps_from_proto": { "total": 94.51138953098462, "count": 63328, "is_parallel": true, "self": 18.93692297001826, "children": { "_process_rank_one_or_two_observation": { "total": 75.57446656096636, "count": 506624, "is_parallel": true, "self": 75.57446656096636 } } } } } } } } } } }, "trainer_advance": { "total": 663.017422247023, "count": 63329, "self": 2.409980374038696, "children": { "process_trajectory": { "total": 124.5537598599849, "count": 63329, "self": 124.34986303598498, "children": { "RLTrainer._checkpoint": { "total": 0.20389682399991216, "count": 2, "self": 0.20389682399991216 } } }, "_update_policy": { "total": 536.0536820129994, "count": 449, "self": 294.9333767510291, "children": { "TorchPPOOptimizer.update": { "total": 241.12030526197032, "count": 22755, "self": 241.12030526197032 } } } } } } }, "trainer_threads": { "total": 9.989998943638057e-07, "count": 1, "self": 9.989998943638057e-07 }, "TrainerController._save_models": { "total": 0.09568970400005128, "count": 1, "self": 0.0015359399999397283, "children": { "RLTrainer._checkpoint": { "total": 0.09415376400011155, "count": 1, "self": 0.09415376400011155 } } } } } } }