{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.44011664390563965, "min": 0.44011664390563965, "max": 1.4029858112335205, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13126.0390625, "min": 13126.0390625, "max": 42560.9765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989933.0, "min": 29952.0, "max": 989933.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989933.0, "min": 29952.0, "max": 989933.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5777921676635742, "min": -0.09090372920036316, "max": 0.5817480087280273, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 161.20401000976562, "min": -21.907798767089844, "max": 164.0529327392578, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008946703746914864, "min": -0.006395567674189806, "max": 0.5310140252113342, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.4961302280426025, "min": -1.733198881149292, "max": 125.8503189086914, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07004542917794813, "min": 0.06468445404676632, "max": 0.07393118554765314, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.980636008491274, "min": 0.5009785290682373, "max": 1.0530875019721149, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016674809737499647, "min": 0.0007331115997585904, "max": 0.017010113332833584, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23344733632499504, "min": 0.00885103431025326, "max": 0.2381415866596702, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.508368925814283e-06, "min": 7.508368925814283e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010511716496139996, "min": 0.00010511716496139996, "max": 0.0035077886307372, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250275714285716, "min": 0.10250275714285716, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350386000000002, "min": 1.3886848, "max": 2.5692627999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002600254385714285, "min": 0.0002600254385714285, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036403561399999994, "min": 0.0036403561399999994, "max": 0.11694935371999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009841570630669594, "min": 0.009841570630669594, "max": 0.5599178671836853, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1377819925546646, "min": 0.1377819925546646, "max": 3.9194250106811523, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 329.7931034482759, "min": 306.72340425531917, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28692.0, "min": 15984.0, "max": 32327.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6228045285256072, "min": -1.0000000521540642, "max": 1.691548374872054, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 142.80679851025343, "min": -29.81740166991949, "max": 157.313998863101, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6228045285256072, "min": -1.0000000521540642, "max": 1.691548374872054, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 142.80679851025343, "min": -29.81740166991949, "max": 157.313998863101, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.033978092623080804, "min": 0.03256384932914228, "max": 11.95184032060206, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9900721508311108, "min": 2.9585949972533854, "max": 191.22944512963295, "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": "1748551908", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748554121" }, "total": 2213.004740252, "count": 1, "self": 1.2636512169997332, "children": { "run_training.setup": { "total": 0.019928865000110818, "count": 1, "self": 0.019928865000110818 }, "TrainerController.start_learning": { "total": 2211.72116017, "count": 1, "self": 1.309291178028161, "children": { "TrainerController._reset_env": { "total": 2.295816489000117, "count": 1, "self": 2.295816489000117 }, "TrainerController.advance": { "total": 2207.980407852972, "count": 63914, "self": 1.377729167965299, "children": { "env_step": { "total": 1534.303165643989, "count": 63914, "self": 1387.1106705290988, "children": { "SubprocessEnvManager._take_step": { "total": 146.45163331298045, "count": 63914, "self": 4.562752177008406, "children": { "TorchPolicy.evaluate": { "total": 141.88888113597204, "count": 62575, "self": 141.88888113597204 } } }, "workers": { "total": 0.7408618019096593, "count": 63914, "self": 0.0, "children": { "worker_root": { "total": 2206.84294106294, "count": 63914, "is_parallel": true, "self": 927.3783936069462, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018533410000145523, "count": 1, "is_parallel": true, "self": 0.0006273300000430027, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012260109999715496, "count": 8, "is_parallel": true, "self": 0.0012260109999715496 } } }, "UnityEnvironment.step": { "total": 0.049522432999992816, "count": 1, "is_parallel": true, "self": 0.0005058610001924535, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004622219998964283, "count": 1, "is_parallel": true, "self": 0.0004622219998964283 }, "communicator.exchange": { "total": 0.046969683999805056, "count": 1, "is_parallel": true, "self": 0.046969683999805056 }, "steps_from_proto": { "total": 0.0015846660000988777, "count": 1, "is_parallel": true, "self": 0.0003319250001823093, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012527409999165684, "count": 8, "is_parallel": true, "self": 0.0012527409999165684 } } } } } } }, "UnityEnvironment.step": { "total": 1279.4645474559939, "count": 63913, "is_parallel": true, "self": 31.87360894899416, "children": { "UnityEnvironment._generate_step_input": { "total": 23.079376943929446, "count": 63913, "is_parallel": true, "self": 23.079376943929446 }, "communicator.exchange": { "total": 1130.8581935390255, "count": 63913, "is_parallel": true, "self": 1130.8581935390255 }, "steps_from_proto": { "total": 93.65336802404477, "count": 63913, "is_parallel": true, "self": 18.664885612872013, "children": { "_process_rank_one_or_two_observation": { "total": 74.98848241117275, "count": 511304, "is_parallel": true, "self": 74.98848241117275 } } } } } } } } } } }, "trainer_advance": { "total": 672.2995130410177, "count": 63914, "self": 2.4277108120402318, "children": { "process_trajectory": { "total": 127.85003238897275, "count": 63914, "self": 127.59933200497312, "children": { "RLTrainer._checkpoint": { "total": 0.2507003839996287, "count": 2, "self": 0.2507003839996287 } } }, "_update_policy": { "total": 542.0217698400047, "count": 452, "self": 299.9707779410321, "children": { "TorchPPOOptimizer.update": { "total": 242.0509918989726, "count": 22791, "self": 242.0509918989726 } } } } } } }, "trainer_threads": { "total": 1.5699997675255872e-06, "count": 1, "self": 1.5699997675255872e-06 }, "TrainerController._save_models": { "total": 0.13564308000013625, "count": 1, "self": 0.0019106629997622804, "children": { "RLTrainer._checkpoint": { "total": 0.13373241700037397, "count": 1, "self": 0.13373241700037397 } } } } } } }