{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4152674078941345, "min": 0.4144142270088196, "max": 1.4873461723327637, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12438.08984375, "min": 12405.904296875, "max": 45120.1328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989987.0, "min": 29952.0, "max": 989987.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989987.0, "min": 29952.0, "max": 989987.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.440431147813797, "min": -0.0880875512957573, "max": 0.5137513875961304, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 119.79727172851562, "min": -21.22909927368164, "max": 137.6853790283203, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0021462670993059874, "min": 0.002125638769939542, "max": 0.291562557220459, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.5837846398353577, "min": 0.5760480761528015, "max": 69.10032653808594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06610876958404246, "min": 0.06610876958404246, "max": 0.07483467953949145, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9255227741765945, "min": 0.5238427567764402, "max": 1.0588531359680928, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015704860688989044, "min": 0.0005514116620104862, "max": 0.015947131534977375, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21986804964584664, "min": 0.00716835160613632, "max": 0.22325984148968323, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.715990285178573e-06, "min": 7.715990285178573e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010802386399250003, "min": 0.00010802386399250003, "max": 0.0034867204377599004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257196428571431, "min": 0.10257196428571431, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360075000000003, "min": 1.3886848, "max": 2.4851436000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026693923214285724, "min": 0.00026693923214285724, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003737149250000001, "min": 0.003737149250000001, "max": 0.11623778599000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009400525130331516, "min": 0.009376540780067444, "max": 0.37579742074012756, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13160735368728638, "min": 0.1312715709209442, "max": 2.630581855773926, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 408.43037974683546, "min": 373.88607594936707, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32266.0, "min": 15984.0, "max": 33532.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4143214908581745, "min": -1.0000000521540642, "max": 1.570367980003357, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 111.73139777779579, "min": -28.354001693427563, "max": 120.46119837462902, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4143214908581745, "min": -1.0000000521540642, "max": 1.570367980003357, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 111.73139777779579, "min": -28.354001693427563, "max": 120.46119837462902, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04000037847767596, "min": 0.03609627767840306, "max": 6.940632737241685, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1600298997364007, "min": 2.8516059365938418, "max": 111.05012379586697, "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": "1701846576", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701848711" }, "total": 2134.640489172, "count": 1, "self": 0.49270845900036875, "children": { "run_training.setup": { "total": 0.05828307899992069, "count": 1, "self": 0.05828307899992069 }, "TrainerController.start_learning": { "total": 2134.0894976339996, "count": 1, "self": 1.3098008580245732, "children": { "TrainerController._reset_env": { "total": 3.6103518040001745, "count": 1, "self": 3.6103518040001745 }, "TrainerController.advance": { "total": 2129.090813978975, "count": 63710, "self": 1.4095461139518193, "children": { "env_step": { "total": 1495.6553255830074, "count": 63710, "self": 1366.4906796520283, "children": { "SubprocessEnvManager._take_step": { "total": 128.3544857889699, "count": 63710, "self": 4.552456846000723, "children": { "TorchPolicy.evaluate": { "total": 123.80202894296917, "count": 62555, "self": 123.80202894296917 } } }, "workers": { "total": 0.8101601420091811, "count": 63710, "self": 0.0, "children": { "worker_root": { "total": 2129.777755907979, "count": 63710, "is_parallel": true, "self": 876.7723385379888, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005010424999909446, "count": 1, "is_parallel": true, "self": 0.003645970000206944, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013644549997025024, "count": 8, "is_parallel": true, "self": 0.0013644549997025024 } } }, "UnityEnvironment.step": { "total": 0.051651566000145976, "count": 1, "is_parallel": true, "self": 0.0006253910003124474, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005072000001291599, "count": 1, "is_parallel": true, "self": 0.0005072000001291599 }, "communicator.exchange": { "total": 0.048678019999897515, "count": 1, "is_parallel": true, "self": 0.048678019999897515 }, "steps_from_proto": { "total": 0.0018409549998068542, "count": 1, "is_parallel": true, "self": 0.0004140679995998653, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014268870002069889, "count": 8, "is_parallel": true, "self": 0.0014268870002069889 } } } } } } }, "UnityEnvironment.step": { "total": 1253.0054173699903, "count": 63709, "is_parallel": true, "self": 34.87256058493995, "children": { "UnityEnvironment._generate_step_input": { "total": 24.281446168042066, "count": 63709, "is_parallel": true, "self": 24.281446168042066 }, "communicator.exchange": { "total": 1095.7944597869907, "count": 63709, "is_parallel": true, "self": 1095.7944597869907 }, "steps_from_proto": { "total": 98.05695083001751, "count": 63709, "is_parallel": true, "self": 19.185711559044876, "children": { "_process_rank_one_or_two_observation": { "total": 78.87123927097264, "count": 509672, "is_parallel": true, "self": 78.87123927097264 } } } } } } } } } } }, "trainer_advance": { "total": 632.0259422820159, "count": 63710, "self": 2.550162473999535, "children": { "process_trajectory": { "total": 125.63742447201867, "count": 63710, "self": 125.46807761201853, "children": { "RLTrainer._checkpoint": { "total": 0.16934686000013244, "count": 2, "self": 0.16934686000013244 } } }, "_update_policy": { "total": 503.8383553359977, "count": 452, "self": 299.8175377309519, "children": { "TorchPPOOptimizer.update": { "total": 204.02081760504575, "count": 22755, "self": 204.02081760504575 } } } } } } }, "trainer_threads": { "total": 1.222999799210811e-06, "count": 1, "self": 1.222999799210811e-06 }, "TrainerController._save_models": { "total": 0.07852976999993189, "count": 1, "self": 0.0012616160001925891, "children": { "RLTrainer._checkpoint": { "total": 0.0772681539997393, "count": 1, "self": 0.0772681539997393 } } } } } } }