{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6467046737670898, "min": 0.602130651473999, "max": 1.4582184553146362, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19370.09765625, "min": 18035.017578125, "max": 44236.515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989921.0, "min": 29952.0, "max": 989921.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989921.0, "min": 29952.0, "max": 989921.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4030449688434601, "min": -0.11876165121793747, "max": 0.4789590537548065, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 108.01605224609375, "min": -28.859081268310547, "max": 132.67166137695312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.17946414649486542, "min": -0.17946414649486542, "max": 0.329105943441391, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -48.09638977050781, "min": -48.09638977050781, "max": 78.29637145996094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07179295801740539, "min": 0.06523902988020058, "max": 0.07473968943496836, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0051014122436754, "min": 0.48957676437784436, "max": 1.0943768605260022, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.03980421142408713, "min": 0.0010826562980246538, "max": 0.03980421142408713, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.5572589599372199, "min": 0.014297832176139466, "max": 0.5572589599372199, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.641847452750002e-06, "min": 7.641847452750002e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010698586433850002, "min": 0.00010698586433850002, "max": 0.0036326974891008994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254724999999999, "min": 0.10254724999999999, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356615, "min": 1.3886848, "max": 2.6108991, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002644702750000001, "min": 0.0002644702750000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003702583850000001, "min": 0.003702583850000001, "max": 0.12110882009000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010382057167589664, "min": 0.010382057167589664, "max": 0.3943900763988495, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14534880220890045, "min": 0.14534880220890045, "max": 2.760730504989624, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 458.04285714285714, "min": 373.09090909090907, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32063.0, "min": 15984.0, "max": 33962.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.259869534144367, "min": -1.0000000521540642, "max": 1.5174149841070175, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 86.93099785596132, "min": -27.994001761078835, "max": 121.3931987285614, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.259869534144367, "min": -1.0000000521540642, "max": 1.5174149841070175, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 86.93099785596132, "min": -27.994001761078835, "max": 121.3931987285614, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.047867476151188144, "min": 0.04076227692202302, "max": 7.473329659551382, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.302855854431982, "min": 3.1386953229957726, "max": 119.57327455282211, "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": "1714049523", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714051591" }, "total": 2067.30689718, "count": 1, "self": 0.47654444499994497, "children": { "run_training.setup": { "total": 0.08075655600009668, "count": 1, "self": 0.08075655600009668 }, "TrainerController.start_learning": { "total": 2066.749596179, "count": 1, "self": 1.22148773300205, "children": { "TrainerController._reset_env": { "total": 2.237377553999977, "count": 1, "self": 2.237377553999977 }, "TrainerController.advance": { "total": 2063.200044865998, "count": 63615, "self": 1.2912681249372326, "children": { "env_step": { "total": 1436.7500104920587, "count": 63615, "self": 1314.1583667670889, "children": { "SubprocessEnvManager._take_step": { "total": 121.83377664398381, "count": 63615, "self": 4.5382840369316, "children": { "TorchPolicy.evaluate": { "total": 117.29549260705221, "count": 62572, "self": 117.29549260705221 } } }, "workers": { "total": 0.7578670809859887, "count": 63615, "self": 0.0, "children": { "worker_root": { "total": 2061.992628678942, "count": 63615, "is_parallel": true, "self": 861.941289483909, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020728080000935734, "count": 1, "is_parallel": true, "self": 0.0006035259998498077, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014692820002437657, "count": 8, "is_parallel": true, "self": 0.0014692820002437657 } } }, "UnityEnvironment.step": { "total": 0.048806190000050265, "count": 1, "is_parallel": true, "self": 0.0006457829999817477, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042907799979730044, "count": 1, "is_parallel": true, "self": 0.00042907799979730044 }, "communicator.exchange": { "total": 0.046111346000088815, "count": 1, "is_parallel": true, "self": 0.046111346000088815 }, "steps_from_proto": { "total": 0.0016199830001824012, "count": 1, "is_parallel": true, "self": 0.00033791100031521637, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012820719998671848, "count": 8, "is_parallel": true, "self": 0.0012820719998671848 } } } } } } }, "UnityEnvironment.step": { "total": 1200.0513391950328, "count": 63614, "is_parallel": true, "self": 33.70735941696921, "children": { "UnityEnvironment._generate_step_input": { "total": 23.633554056996445, "count": 63614, "is_parallel": true, "self": 23.633554056996445 }, "communicator.exchange": { "total": 1045.0781443430728, "count": 63614, "is_parallel": true, "self": 1045.0781443430728 }, "steps_from_proto": { "total": 97.63228137799433, "count": 63614, "is_parallel": true, "self": 19.22741163907449, "children": { "_process_rank_one_or_two_observation": { "total": 78.40486973891984, "count": 508912, "is_parallel": true, "self": 78.40486973891984 } } } } } } } } } } }, "trainer_advance": { "total": 625.1587662490019, "count": 63615, "self": 2.360376409950277, "children": { "process_trajectory": { "total": 123.44139810704814, "count": 63615, "self": 123.25078979004843, "children": { "RLTrainer._checkpoint": { "total": 0.1906083169997146, "count": 2, "self": 0.1906083169997146 } } }, "_update_policy": { "total": 499.3569917320035, "count": 451, "self": 293.5076613689737, "children": { "TorchPPOOptimizer.update": { "total": 205.84933036302982, "count": 22791, "self": 205.84933036302982 } } } } } } }, "trainer_threads": { "total": 1.5099999473022763e-06, "count": 1, "self": 1.5099999473022763e-06 }, "TrainerController._save_models": { "total": 0.09068451600023764, "count": 1, "self": 0.0013790880002488848, "children": { "RLTrainer._checkpoint": { "total": 0.08930542799998875, "count": 1, "self": 0.08930542799998875 } } } } } } }