{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13221512734889984, "min": 0.1272667795419693, "max": 1.407233715057373, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 3989.723876953125, "min": 3834.293701171875, "max": 42689.84375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999942.0, "min": 29952.0, "max": 2999942.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999942.0, "min": 29952.0, "max": 2999942.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7229605913162231, "min": -0.10576966404914856, "max": 0.8156408667564392, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 212.5504150390625, "min": -25.173179626464844, "max": 248.7704620361328, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.019991837441921234, "min": -0.01818006858229637, "max": 0.29719290137290955, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.877600193023682, "min": -5.163139343261719, "max": 71.3262939453125, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06657112411390312, "min": 0.06383400985330427, "max": 0.07328374463483991, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9319957375946437, "min": 0.4724973442946861, "max": 1.09794457545892, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013803438742968568, "min": 0.00013600046863911338, "max": 0.017198874486590892, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19324814240155996, "min": 0.001768006092308474, "max": 0.24078424281227248, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4789137927761899e-06, "min": 1.4789137927761899e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0704793098866658e-05, "min": 2.0704793098866658e-05, "max": 0.0037176655607782006, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1004929380952381, "min": 0.1004929380952381, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4069011333333334, "min": 1.3897045333333333, "max": 2.6624904333333332, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.924451571428569e-05, "min": 5.924451571428569e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008294232199999997, "min": 0.0008294232199999997, "max": 0.12393825782, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009143837727606297, "min": 0.009143837727606297, "max": 0.476852685213089, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1280137300491333, "min": 0.1280137300491333, "max": 3.3379688262939453, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 256.635593220339, "min": 221.64341085271317, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30283.0, "min": 15984.0, "max": 33490.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6925050709712304, "min": -1.0000000521540642, "max": 1.7783565739559573, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 199.71559837460518, "min": -32.000001668930054, "max": 239.56899818778038, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6925050709712304, "min": -1.0000000521540642, "max": 1.7783565739559573, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 199.71559837460518, "min": -32.000001668930054, "max": 239.56899818778038, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.024438495906767874, "min": 0.024358566517346643, "max": 9.298519301228225, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.883742516998609, "min": 2.8441981873183977, "max": 148.7763088196516, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1702584699", "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": "1702592183" }, "total": 7483.921704064999, "count": 1, "self": 0.49338256899955013, "children": { "run_training.setup": { "total": 0.05729486400014139, "count": 1, "self": 0.05729486400014139 }, "TrainerController.start_learning": { "total": 7483.3710266319995, "count": 1, "self": 4.676149400040231, "children": { "TrainerController._reset_env": { "total": 2.0217331300000296, "count": 1, "self": 2.0217331300000296 }, "TrainerController.advance": { "total": 7476.582755401959, "count": 193591, "self": 4.692864257228393, "children": { "env_step": { "total": 5545.850490101838, "count": 193591, "self": 5126.316260773696, "children": { "SubprocessEnvManager._take_step": { "total": 416.6082461840924, "count": 193591, "self": 15.383216534906751, "children": { "TorchPolicy.evaluate": { "total": 401.2250296491857, "count": 187561, "self": 401.2250296491857 } } }, "workers": { "total": 2.9259831440494963, "count": 193591, "self": 0.0, "children": { "worker_root": { "total": 7466.419520835796, "count": 193591, "is_parallel": true, "self": 2731.018649834743, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018593709999095154, "count": 1, "is_parallel": true, "self": 0.0005705320002107328, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012888389996987826, "count": 8, "is_parallel": true, "self": 0.0012888389996987826 } } }, "UnityEnvironment.step": { "total": 0.049614775000009104, "count": 1, "is_parallel": true, "self": 0.0005971940001927578, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005256449999251345, "count": 1, "is_parallel": true, "self": 0.0005256449999251345 }, "communicator.exchange": { "total": 0.04672557300000335, "count": 1, "is_parallel": true, "self": 0.04672557300000335 }, "steps_from_proto": { "total": 0.0017663629998878605, "count": 1, "is_parallel": true, "self": 0.0003621059997840348, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014042570001038257, "count": 8, "is_parallel": true, "self": 0.0014042570001038257 } } } } } } }, "UnityEnvironment.step": { "total": 4735.400871001053, "count": 193590, "is_parallel": true, "self": 107.32194510208228, "children": { "UnityEnvironment._generate_step_input": { "total": 75.9658616841889, "count": 193590, "is_parallel": true, "self": 75.9658616841889 }, "communicator.exchange": { "total": 4238.666393592782, "count": 193590, "is_parallel": true, "self": 4238.666393592782 }, "steps_from_proto": { "total": 313.44667062199983, "count": 193590, "is_parallel": true, "self": 65.43094215963265, "children": { "_process_rank_one_or_two_observation": { "total": 248.01572846236718, "count": 1548720, "is_parallel": true, "self": 248.01572846236718 } } } } } } } } } } }, "trainer_advance": { "total": 1926.0394010428922, "count": 193591, "self": 9.292970619781272, "children": { "process_trajectory": { "total": 402.68476739011567, "count": 193591, "self": 402.07738878211467, "children": { "RLTrainer._checkpoint": { "total": 0.6073786080009995, "count": 6, "self": 0.6073786080009995 } } }, "_update_policy": { "total": 1514.0616630329953, "count": 1381, "self": 896.679085334916, "children": { "TorchPPOOptimizer.update": { "total": 617.3825776980793, "count": 68421, "self": 617.3825776980793 } } } } } } }, "trainer_threads": { "total": 1.22199890029151e-06, "count": 1, "self": 1.22199890029151e-06 }, "TrainerController._save_models": { "total": 0.09038747800150304, "count": 1, "self": 0.0016175720011233352, "children": { "RLTrainer._checkpoint": { "total": 0.0887699060003797, "count": 1, "self": 0.0887699060003797 } } } } } } }