{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4273618757724762, "min": 0.42269015312194824, "max": 1.4904751777648926, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12902.91015625, "min": 12626.6005859375, "max": 45215.0546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989925.0, "min": 29903.0, "max": 989925.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989925.0, "min": 29903.0, "max": 989925.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5286481380462646, "min": -0.21094124019145966, "max": 0.5336003303527832, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 147.49282836914062, "min": -49.993072509765625, "max": 147.49282836914062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.012570939026772976, "min": -0.04996778815984726, "max": 0.19601817429065704, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.5072920322418213, "min": -12.292076110839844, "max": 47.240379333496094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07027118197082691, "min": 0.06608855703929427, "max": 0.0742880380105916, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9837965475915768, "min": 0.5115610367364929, "max": 1.0994388867642126, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015721007701562567, "min": 0.0002924120717638371, "max": 0.015721007701562567, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22009410782187594, "min": 0.004093769004693719, "max": 0.22009410782187594, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.269697576800001e-06, "min": 7.269697576800001e-06, "max": 0.0002952350158740429, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010177576607520001, "min": 0.00010177576607520001, "max": 0.0035082500305834005, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242320000000002, "min": 0.10242320000000002, "max": 0.19841167142857144, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339248000000002, "min": 1.3888817, "max": 2.5694166000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025207768, "min": 0.00025207768, "max": 0.009841325975714285, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035290875200000003, "min": 0.0035290875200000003, "max": 0.11696471834000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0081326300278306, "min": 0.0081326300278306, "max": 0.35708338022232056, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11385681480169296, "min": 0.11385681480169296, "max": 2.4995837211608887, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 329.9789473684211, "min": 329.9789473684211, "max": 993.53125, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31348.0, "min": 16702.0, "max": 32567.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6278968214204437, "min": -0.9100303541530262, "max": 1.6278968214204437, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 154.65019803494215, "min": -30.031001687049866, "max": 154.65019803494215, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6278968214204437, "min": -0.9100303541530262, "max": 1.6278968214204437, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 154.65019803494215, "min": -30.031001687049866, "max": 154.65019803494215, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.027983644718647397, "min": 0.027983644718647397, "max": 7.0415510158328445, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6584462482715026, "min": 2.450503786909394, "max": 119.70636726915836, "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": "1728137646", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1728139867" }, "total": 2220.514567525, "count": 1, "self": 1.133186102000309, "children": { "run_training.setup": { "total": 0.05346232199997303, "count": 1, "self": 0.05346232199997303 }, "TrainerController.start_learning": { "total": 2219.3279191009997, "count": 1, "self": 1.3353799730239189, "children": { "TrainerController._reset_env": { "total": 3.0478495800000474, "count": 1, "self": 3.0478495800000474 }, "TrainerController.advance": { "total": 2214.818198091976, "count": 63749, "self": 1.357751519003159, "children": { "env_step": { "total": 1540.7794381819774, "count": 63749, "self": 1390.6929151170702, "children": { "SubprocessEnvManager._take_step": { "total": 149.2980225149334, "count": 63749, "self": 4.446747082960485, "children": { "TorchPolicy.evaluate": { "total": 144.8512754319729, "count": 62548, "self": 144.8512754319729 } } }, "workers": { "total": 0.7885005499736621, "count": 63749, "self": 0.0, "children": { "worker_root": { "total": 2214.125014582948, "count": 63749, "is_parallel": true, "self": 938.9947991679019, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025088950000053956, "count": 1, "is_parallel": true, "self": 0.0007349530000055893, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017739419999998063, "count": 8, "is_parallel": true, "self": 0.0017739419999998063 } } }, "UnityEnvironment.step": { "total": 0.0490300120000029, "count": 1, "is_parallel": true, "self": 0.0006052389999808838, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048553599998513164, "count": 1, "is_parallel": true, "self": 0.00048553599998513164 }, "communicator.exchange": { "total": 0.04635134300002619, "count": 1, "is_parallel": true, "self": 0.04635134300002619 }, "steps_from_proto": { "total": 0.0015878940000106923, "count": 1, "is_parallel": true, "self": 0.00034681799991176376, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012410760000989285, "count": 8, "is_parallel": true, "self": 0.0012410760000989285 } } } } } } }, "UnityEnvironment.step": { "total": 1275.1302154150462, "count": 63748, "is_parallel": true, "self": 32.855740975063554, "children": { "UnityEnvironment._generate_step_input": { "total": 23.077712360976534, "count": 63748, "is_parallel": true, "self": 23.077712360976534 }, "communicator.exchange": { "total": 1125.4728127209962, "count": 63748, "is_parallel": true, "self": 1125.4728127209962 }, "steps_from_proto": { "total": 93.7239493580098, "count": 63748, "is_parallel": true, "self": 18.634363453166543, "children": { "_process_rank_one_or_two_observation": { "total": 75.08958590484326, "count": 509984, "is_parallel": true, "self": 75.08958590484326 } } } } } } } } } } }, "trainer_advance": { "total": 672.6810083909952, "count": 63749, "self": 2.5086155749434056, "children": { "process_trajectory": { "total": 130.4581114660469, "count": 63749, "self": 130.14209754704672, "children": { "RLTrainer._checkpoint": { "total": 0.31601391900017006, "count": 2, "self": 0.31601391900017006 } } }, "_update_policy": { "total": 539.714281350005, "count": 450, "self": 305.2316838690154, "children": { "TorchPPOOptimizer.update": { "total": 234.48259748098957, "count": 22770, "self": 234.48259748098957 } } } } } } }, "trainer_threads": { "total": 1.4869997357891407e-06, "count": 1, "self": 1.4869997357891407e-06 }, "TrainerController._save_models": { "total": 0.12648996899997655, "count": 1, "self": 0.001917989000048692, "children": { "RLTrainer._checkpoint": { "total": 0.12457197999992786, "count": 1, "self": 0.12457197999992786 } } } } } } }