{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.21462424099445343, "min": 0.1937692016363144, "max": 1.4697425365447998, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 6483.369140625, "min": 5837.87841796875, "max": 44586.109375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999933.0, "min": 29952.0, "max": 2999933.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999933.0, "min": 29952.0, "max": 2999933.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7234064936637878, "min": -0.12110161036252975, "max": 0.7526270151138306, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 211.95809936523438, "min": -29.185487747192383, "max": 219.01446533203125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00856872834265232, "min": -0.024014851078391075, "max": 0.2539796829223633, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.5106372833251953, "min": -6.484009742736816, "max": 60.95512390136719, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.069572044165744, "min": 0.06424086001295748, "max": 0.07535032406566643, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9740086183204161, "min": 0.5092744208608377, "max": 1.0744941707137816, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016082872423881085, "min": 0.00011680961082599403, "max": 0.01943405392165813, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2251602139343352, "min": 0.0015185249407379225, "max": 0.29151080882487196, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4348709503142862e-06, "min": 1.4348709503142862e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0088193304400005e-05, "min": 2.0088193304400005e-05, "max": 0.003759231946922733, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10047825714285716, "min": 0.10047825714285716, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4066956000000002, "min": 1.3897045333333333, "max": 2.6775243333333343, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.777788857142859e-05, "min": 5.777788857142859e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008088904400000002, "min": 0.0008088904400000002, "max": 0.12532241894, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004851572215557098, "min": 0.004364532418549061, "max": 0.3916610777378082, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06792201101779938, "min": 0.061103455722332, "max": 2.7416274547576904, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 247.31404958677686, "min": 236.75, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29925.0, "min": 15984.0, "max": 33157.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7523688407706433, "min": -1.0000000521540642, "max": 1.7523688407706433, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 213.78899857401848, "min": -32.000001668930054, "max": 213.78899857401848, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7523688407706433, "min": -1.0000000521540642, "max": 1.7523688407706433, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 213.78899857401848, "min": -32.000001668930054, "max": 213.78899857401848, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.012651914326673503, "min": 0.012395628608189801, "max": 7.578579317778349, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.5435335478541674, "min": 1.320726834310335, "max": 121.25726908445358, "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": "1714251468", "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": "1714262141" }, "total": 10673.16093311, "count": 1, "self": 0.6915744130019448, "children": { "run_training.setup": { "total": 0.07485801999996511, "count": 1, "self": 0.07485801999996511 }, "TrainerController.start_learning": { "total": 10672.394500676999, "count": 1, "self": 7.8759228047129, "children": { "TrainerController._reset_env": { "total": 3.7954186669999217, "count": 1, "self": 3.7954186669999217 }, "TrainerController.advance": { "total": 10660.621435671286, "count": 193001, "self": 8.34151978517366, "children": { "env_step": { "total": 7332.892414143221, "count": 193001, "self": 6801.331870094117, "children": { "SubprocessEnvManager._take_step": { "total": 526.4764015890751, "count": 193001, "self": 22.39610282023773, "children": { "TorchPolicy.evaluate": { "total": 504.08029876883734, "count": 187568, "self": 504.08029876883734 } } }, "workers": { "total": 5.0841424600287155, "count": 193001, "self": 0.0, "children": { "worker_root": { "total": 10647.456901044838, "count": 193001, "is_parallel": true, "self": 4478.847500907073, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003305173999933686, "count": 1, "is_parallel": true, "self": 0.000909501000023738, "children": { "_process_rank_one_or_two_observation": { "total": 0.002395672999909948, "count": 8, "is_parallel": true, "self": 0.002395672999909948 } } }, "UnityEnvironment.step": { "total": 0.07583503299997574, "count": 1, "is_parallel": true, "self": 0.0008837970001422946, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006119329998455214, "count": 1, "is_parallel": true, "self": 0.0006119329998455214 }, "communicator.exchange": { "total": 0.07211828399999831, "count": 1, "is_parallel": true, "self": 0.07211828399999831 }, "steps_from_proto": { "total": 0.00222101899998961, "count": 1, "is_parallel": true, "self": 0.0006051930004105088, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016158259995791013, "count": 8, "is_parallel": true, "self": 0.0016158259995791013 } } } } } } }, "UnityEnvironment.step": { "total": 6168.609400137765, "count": 193000, "is_parallel": true, "self": 170.38392649622529, "children": { "UnityEnvironment._generate_step_input": { "total": 94.12286494881641, "count": 193000, "is_parallel": true, "self": 94.12286494881641 }, "communicator.exchange": { "total": 5488.245724856997, "count": 193000, "is_parallel": true, "self": 5488.245724856997 }, "steps_from_proto": { "total": 415.85688383572597, "count": 193000, "is_parallel": true, "self": 92.90709607046301, "children": { "_process_rank_one_or_two_observation": { "total": 322.94978776526295, "count": 1544000, "is_parallel": true, "self": 322.94978776526295 } } } } } } } } } } }, "trainer_advance": { "total": 3319.3875017428927, "count": 193001, "self": 17.792276550630504, "children": { "process_trajectory": { "total": 544.1901768462444, "count": 193001, "self": 543.4973281162452, "children": { "RLTrainer._checkpoint": { "total": 0.6928487299992412, "count": 6, "self": 0.6928487299992412 } } }, "_update_policy": { "total": 2757.405048346018, "count": 1385, "self": 1107.4093595001991, "children": { "TorchPPOOptimizer.update": { "total": 1649.9956888458187, "count": 68346, "self": 1649.9956888458187 } } } } } } }, "trainer_threads": { "total": 1.2279997463338077e-06, "count": 1, "self": 1.2279997463338077e-06 }, "TrainerController._save_models": { "total": 0.10172230600073817, "count": 1, "self": 0.0025307670002803206, "children": { "RLTrainer._checkpoint": { "total": 0.09919153900045785, "count": 1, "self": 0.09919153900045785 } } } } } } }