{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4165646731853485, "min": 0.40163546800613403, "max": 1.4806667566299438, "count": 52 }, "Pyramids.Policy.Entropy.sum": { "value": 12223.673828125, "min": 12132.6044921875, "max": 44917.5078125, "count": 52 }, "Pyramids.Step.mean": { "value": 1559875.0, "min": 29952.0, "max": 1559875.0, "count": 52 }, "Pyramids.Step.sum": { "value": 1559875.0, "min": 29952.0, "max": 1559875.0, "count": 52 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5290877223014832, "min": -0.11454473435878754, "max": 0.5587700605392456, "count": 52 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 144.97003173828125, "min": -27.49073600769043, "max": 152.54421997070312, "count": 52 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.006103459279984236, "min": -0.0251805130392313, "max": 0.25557011365890503, "count": 52 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.672347903251648, "min": -6.723196983337402, "max": 61.336830139160156, "count": 52 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06869723334999302, "min": 0.06460764174421672, "max": 0.0727808943636835, "count": 52 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9617612668999023, "min": 0.47909215814434, "max": 1.0839812987844697, "count": 52 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012419828267047196, "min": 9.521335650952962e-05, "max": 0.012419828267047196, "count": 52 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17387759573866074, "min": 0.001237773634623885, "max": 0.17387759573866074, "count": 52 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00014549720864380475, "min": 0.00014549720864380475, "max": 0.00029838354339596195, "count": 52 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0020369609210132665, "min": 0.002027104024298666, "max": 0.0037594509468497324, "count": 52 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1484990523809524, "min": 0.1484990523809524, "max": 0.19946118095238097, "count": 52 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.0789867333333336, "min": 1.3757013333333334, "max": 2.6531502666666675, "count": 52 }, "Pyramids.Policy.Beta.mean": { "value": 0.0048550553328571425, "min": 0.0048550553328571425, "max": 0.009946171977142856, "count": 52 }, "Pyramids.Policy.Beta.sum": { "value": 0.06797077466, "min": 0.06757256319999999, "max": 0.12532971164, "count": 52 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004804596770554781, "min": 0.00433261226862669, "max": 0.3447306454181671, "count": 52 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06726435571908951, "min": 0.06065656989812851, "max": 2.413114547729492, "count": 52 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 377.07894736842104, "min": 345.23809523809524, "max": 999.0, "count": 52 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28658.0, "min": 15984.0, "max": 33896.0, "count": 52 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5176262921212536, "min": -1.0000000521540642, "max": 1.5833095061991895, "count": 52 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 115.33959820121527, "min": -32.000001668930054, "max": 132.99799852073193, "count": 52 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5176262921212536, "min": -1.0000000521540642, "max": 1.5833095061991895, "count": 52 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 115.33959820121527, "min": -32.000001668930054, "max": 132.99799852073193, "count": 52 }, "Pyramids.Policy.RndReward.mean": { "value": 0.018644611067812594, "min": 0.01617049040162653, "max": 6.940789316780865, "count": 52 }, "Pyramids.Policy.RndReward.sum": { "value": 1.4169904411537573, "min": 1.3122262909600977, "max": 111.05262906849384, "count": 52 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 52 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 52 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1736165049", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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=PyramidsTraining --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736168427" }, "total": 3378.282926876, "count": 1, "self": 0.3825557620007203, "children": { "run_training.setup": { "total": 0.07782670900007815, "count": 1, "self": 0.07782670900007815 }, "TrainerController.start_learning": { "total": 3377.8225444049995, "count": 1, "self": 1.9590828259451882, "children": { "TrainerController._reset_env": { "total": 5.535551100000021, "count": 1, "self": 5.535551100000021 }, "TrainerController.advance": { "total": 3370.1835454630545, "count": 100233, "self": 2.102668974996959, "children": { "env_step": { "total": 2278.0289274559677, "count": 100233, "self": 2056.4789919720215, "children": { "SubprocessEnvManager._take_step": { "total": 220.37158759004126, "count": 100233, "self": 6.804709509081363, "children": { "TorchPolicy.evaluate": { "total": 213.5668780809599, "count": 98685, "self": 213.5668780809599 } } }, "workers": { "total": 1.1783478939048564, "count": 100232, "self": 0.0, "children": { "worker_root": { "total": 3370.7720719059885, "count": 100232, "is_parallel": true, "self": 1487.4161913319726, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003491411000027256, "count": 1, "is_parallel": true, "self": 0.0009558240001297236, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025355869998975322, "count": 8, "is_parallel": true, "self": 0.0025355869998975322 } } }, "UnityEnvironment.step": { "total": 0.047565000999952645, "count": 1, "is_parallel": true, "self": 0.0006084649999138492, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004494990000694088, "count": 1, "is_parallel": true, "self": 0.0004494990000694088 }, "communicator.exchange": { "total": 0.04488320100006149, "count": 1, "is_parallel": true, "self": 0.04488320100006149 }, "steps_from_proto": { "total": 0.0016238359999078966, "count": 1, "is_parallel": true, "self": 0.0003395269998236472, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012843090000842494, "count": 8, "is_parallel": true, "self": 0.0012843090000842494 } } } } } } }, "UnityEnvironment.step": { "total": 1883.3558805740158, "count": 100231, "is_parallel": true, "self": 51.207851367937565, "children": { "UnityEnvironment._generate_step_input": { "total": 35.77328111900772, "count": 100231, "is_parallel": true, "self": 35.77328111900772 }, "communicator.exchange": { "total": 1647.3357374390148, "count": 100231, "is_parallel": true, "self": 1647.3357374390148 }, "steps_from_proto": { "total": 149.03901064805586, "count": 100231, "is_parallel": true, "self": 29.171997597124346, "children": { "_process_rank_one_or_two_observation": { "total": 119.86701305093152, "count": 801848, "is_parallel": true, "self": 119.86701305093152 } } } } } } } } } } }, "trainer_advance": { "total": 1090.0519490320899, "count": 100232, "self": 3.579410602092821, "children": { "process_trajectory": { "total": 204.11210338300464, "count": 100232, "self": 203.741378542005, "children": { "RLTrainer._checkpoint": { "total": 0.3707248409996282, "count": 3, "self": 0.3707248409996282 } } }, "_update_policy": { "total": 882.3604350469924, "count": 698, "self": 496.85726357902286, "children": { "TorchPPOOptimizer.update": { "total": 385.50317146796954, "count": 36093, "self": 385.50317146796954 } } } } } } }, "trainer_threads": { "total": 1.6379999578930438e-06, "count": 1, "self": 1.6379999578930438e-06 }, "TrainerController._save_models": { "total": 0.14436337799998, "count": 1, "self": 0.002059250999991491, "children": { "RLTrainer._checkpoint": { "total": 0.1423041269999885, "count": 1, "self": 0.1423041269999885 } } } } } } }