{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6386364698410034, "min": 0.6197202801704407, "max": 1.4369486570358276, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19087.56640625, "min": 18522.19921875, "max": 43591.2734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989982.0, "min": 29924.0, "max": 989982.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989982.0, "min": 29924.0, "max": 989982.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1937706619501114, "min": -0.0976429432630539, "max": 0.3026611804962158, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 49.02397918701172, "min": -23.434307098388672, "max": 78.69190979003906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0186823271214962, "min": -0.01673896610736847, "max": 0.46599769592285156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.72662878036499, "min": -4.268436431884766, "max": 110.44145202636719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06825234124501216, "min": 0.06455889866698443, "max": 0.07438734783504863, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9555327774301702, "min": 0.5950987826803891, "max": 1.0705515693293375, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.009983505197087348, "min": 9.286692631939901e-05, "max": 0.014882415159753182, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.13976907275922287, "min": 0.001300136968471586, "max": 0.16559779972279404, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.628861742792858e-06, "min": 7.628861742792858e-06, "max": 0.00029484315171895, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010680406439910001, "min": 0.00010680406439910001, "max": 0.0036352429882523995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254292142857142, "min": 0.10254292142857142, "max": 0.19828105, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356008999999998, "min": 1.4356008999999998, "max": 2.6117475999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002640378507142858, "min": 0.0002640378507142858, "max": 0.009828276895, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003696529910000001, "min": 0.003696529910000001, "max": 0.12119358524, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012470705434679985, "min": 0.012470705434679985, "max": 0.5592457056045532, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1745898723602295, "min": 0.1745898723602295, "max": 4.473965644836426, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 654.3555555555556, "min": 535.8275862068965, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29446.0, "min": 16467.0, "max": 33408.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.812151079873244, "min": -1.0000000521540642, "max": 1.1537448020073875, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 36.54679859429598, "min": -32.000001668930054, "max": 66.91719851642847, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.812151079873244, "min": -1.0000000521540642, "max": 1.1537448020073875, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 36.54679859429598, "min": -32.000001668930054, "max": 66.91719851642847, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08623908767735379, "min": 0.07814560916951199, "max": 11.805768886033226, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8807589454809204, "min": 3.8807589454809204, "max": 200.69807106256485, "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": "1700001568", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700003751" }, "total": 2183.0824509830004, "count": 1, "self": 0.8472459450003953, "children": { "run_training.setup": { "total": 0.042974134999894886, "count": 1, "self": 0.042974134999894886 }, "TrainerController.start_learning": { "total": 2182.192230903, "count": 1, "self": 1.448006620839351, "children": { "TrainerController._reset_env": { "total": 3.503130933999728, "count": 1, "self": 3.503130933999728 }, "TrainerController.advance": { "total": 2177.1309200071605, "count": 63314, "self": 1.5092999903013151, "children": { "env_step": { "total": 1523.649793151009, "count": 63314, "self": 1386.017517499171, "children": { "SubprocessEnvManager._take_step": { "total": 136.7383825469451, "count": 63314, "self": 4.7798898699034, "children": { "TorchPolicy.evaluate": { "total": 131.9584926770417, "count": 62566, "self": 131.9584926770417 } } }, "workers": { "total": 0.893893104892868, "count": 63314, "self": 0.0, "children": { "worker_root": { "total": 2177.2658478540952, "count": 63314, "is_parallel": true, "self": 917.9149919530596, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020864269999947282, "count": 1, "is_parallel": true, "self": 0.0006521650002468959, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014342619997478323, "count": 8, "is_parallel": true, "self": 0.0014342619997478323 } } }, "UnityEnvironment.step": { "total": 0.04924592199995459, "count": 1, "is_parallel": true, "self": 0.0005668870003319171, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005462839999381686, "count": 1, "is_parallel": true, "self": 0.0005462839999381686 }, "communicator.exchange": { "total": 0.04647793299955083, "count": 1, "is_parallel": true, "self": 0.04647793299955083 }, "steps_from_proto": { "total": 0.0016548180001336732, "count": 1, "is_parallel": true, "self": 0.0003386530006537214, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013161649994799518, "count": 8, "is_parallel": true, "self": 0.0013161649994799518 } } } } } } }, "UnityEnvironment.step": { "total": 1259.3508559010356, "count": 63313, "is_parallel": true, "self": 35.19199873426351, "children": { "UnityEnvironment._generate_step_input": { "total": 26.289097600966215, "count": 63313, "is_parallel": true, "self": 26.289097600966215 }, "communicator.exchange": { "total": 1093.6041300509642, "count": 63313, "is_parallel": true, "self": 1093.6041300509642 }, "steps_from_proto": { "total": 104.26562951484175, "count": 63313, "is_parallel": true, "self": 21.109831211442724, "children": { "_process_rank_one_or_two_observation": { "total": 83.15579830339902, "count": 506504, "is_parallel": true, "self": 83.15579830339902 } } } } } } } } } } }, "trainer_advance": { "total": 651.9718268658503, "count": 63314, "self": 2.7346209687980263, "children": { "process_trajectory": { "total": 129.03575738405561, "count": 63314, "self": 128.84124739905656, "children": { "RLTrainer._checkpoint": { "total": 0.19450998499905836, "count": 2, "self": 0.19450998499905836 } } }, "_update_policy": { "total": 520.2014485129966, "count": 456, "self": 311.27103649299715, "children": { "TorchPPOOptimizer.update": { "total": 208.9304120199995, "count": 22755, "self": 208.9304120199995 } } } } } } }, "trainer_threads": { "total": 1.3110002328176051e-06, "count": 1, "self": 1.3110002328176051e-06 }, "TrainerController._save_models": { "total": 0.1101720300002853, "count": 1, "self": 0.0017081639998650644, "children": { "RLTrainer._checkpoint": { "total": 0.10846386600042024, "count": 1, "self": 0.10846386600042024 } } } } } } }