{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.40660443902015686, "min": 0.3838774263858795, "max": 1.3838720321655273, "count": 20 }, "Pyramids.Policy.Entropy.sum": { "value": 20323.716796875, "min": 19058.74609375, "max": 70632.828125, "count": 20 }, "Pyramids.Step.mean": { "value": 999902.0, "min": 49982.0, "max": 999902.0, "count": 20 }, "Pyramids.Step.sum": { "value": 999902.0, "min": 49982.0, "max": 999902.0, "count": 20 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5106868147850037, "min": -0.10902372002601624, "max": 0.5106868147850037, "count": 20 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 230.8304443359375, "min": -43.60948944091797, "max": 230.8304443359375, "count": 20 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.018002863973379135, "min": 0.017526134848594666, "max": 0.27170729637145996, "count": 20 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.13729476928711, "min": 7.298983573913574, "max": 108.68292236328125, "count": 20 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0690960958714177, "min": 0.06685300014880363, "max": 0.07348646662135302, "count": 20 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.6583063009140246, "min": 1.0288105326989423, "max": 1.7034627192473386, "count": 20 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015689400035530914, "min": 0.0004058652203409273, "max": 0.017001819814943114, "count": 20 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.3765456008527419, "min": 0.008697785586991082, "max": 0.40804367555863474, "count": 20 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.360097546666664e-06, "min": 7.360097546666664e-06, "max": 0.00029159310280229997, "count": 20 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00017664234111999994, "min": 0.00017664234111999994, "max": 0.0054513657828781995, "count": 20 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245333333333334, "min": 0.10245333333333334, "max": 0.1971977, "count": 20 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.45888, "min": 2.45888, "max": 4.0171218, "count": 20 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025508799999999994, "min": 0.00025508799999999994, "max": 0.00972005023, "count": 20 }, "Pyramids.Policy.Beta.sum": { "value": 0.006122111999999999, "min": 0.006122111999999999, "max": 0.18175046781999998, "count": 20 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015770716592669487, "min": 0.015770716592669487, "max": 0.37413766980171204, "count": 20 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.3784972131252289, "min": 0.3784972131252289, "max": 5.237927436828613, "count": 20 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 355.95620437956205, "min": 355.95620437956205, "max": 999.0, "count": 20 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 48766.0, "min": 47053.0, "max": 52985.0, "count": 20 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5564291726281172, "min": -1.0000000521540642, "max": 1.5564291726281172, "count": 20 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 213.23079665005207, "min": -48.00000250339508, "max": 213.23079665005207, "count": 20 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5564291726281172, "min": -1.0000000521540642, "max": 1.5564291726281172, "count": 20 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 213.23079665005207, "min": -48.00000250339508, "max": 213.23079665005207, "count": 20 }, "Pyramids.Policy.RndReward.mean": { "value": 0.057838770586890624, "min": 0.057838770586890624, "max": 5.367142829267929, "count": 20 }, "Pyramids.Policy.RndReward.sum": { "value": 7.923911570404016, "min": 7.923911570404016, "max": 257.6228558048606, "count": 20 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704275892", "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-3 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704278030" }, "total": 2138.0222330259994, "count": 1, "self": 0.9853462019991639, "children": { "run_training.setup": { "total": 0.04736289700031193, "count": 1, "self": 0.04736289700031193 }, "TrainerController.start_learning": { "total": 2136.989523927, "count": 1, "self": 1.458595546028846, "children": { "TrainerController._reset_env": { "total": 2.147141593000015, "count": 1, "self": 2.147141593000015 }, "TrainerController.advance": { "total": 2133.255490715972, "count": 63628, "self": 1.5977552797594399, "children": { "env_step": { "total": 1490.3827759572332, "count": 63628, "self": 1354.185206475171, "children": { "SubprocessEnvManager._take_step": { "total": 135.26424939209664, "count": 63628, "self": 4.834128640190102, "children": { "TorchPolicy.evaluate": { "total": 130.43012075190654, "count": 62551, "self": 130.43012075190654 } } }, "workers": { "total": 0.9333200899654912, "count": 63628, "self": 0.0, "children": { "worker_root": { "total": 2131.672288137017, "count": 63628, "is_parallel": true, "self": 900.1139222690681, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017603739997866796, "count": 1, "is_parallel": true, "self": 0.0005314810023264727, "children": { "_process_rank_one_or_two_observation": { "total": 0.001228892997460207, "count": 8, "is_parallel": true, "self": 0.001228892997460207 } } }, "UnityEnvironment.step": { "total": 0.04862397000033525, "count": 1, "is_parallel": true, "self": 0.0005931800005782861, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004881089998889365, "count": 1, "is_parallel": true, "self": 0.0004881089998889365 }, "communicator.exchange": { "total": 0.04590963299961004, "count": 1, "is_parallel": true, "self": 0.04590963299961004 }, "steps_from_proto": { "total": 0.0016330480002579861, "count": 1, "is_parallel": true, "self": 0.00035718700019060634, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012758610000673798, "count": 8, "is_parallel": true, "self": 0.0012758610000673798 } } } } } } }, "UnityEnvironment.step": { "total": 1231.5583658679489, "count": 63627, "is_parallel": true, "self": 34.945650922931236, "children": { "UnityEnvironment._generate_step_input": { "total": 24.486377486137826, "count": 63627, "is_parallel": true, "self": 24.486377486137826 }, "communicator.exchange": { "total": 1073.1361114249412, "count": 63627, "is_parallel": true, "self": 1073.1361114249412 }, "steps_from_proto": { "total": 98.9902260339386, "count": 63627, "is_parallel": true, "self": 20.087128791734358, "children": { "_process_rank_one_or_two_observation": { "total": 78.90309724220424, "count": 509016, "is_parallel": true, "self": 78.90309724220424 } } } } } } } } } } }, "trainer_advance": { "total": 641.2749594789793, "count": 63628, "self": 2.883373502001632, "children": { "process_trajectory": { "total": 128.47727592296815, "count": 63628, "self": 128.2043659059682, "children": { "RLTrainer._checkpoint": { "total": 0.2729100169999583, "count": 2, "self": 0.2729100169999583 } } }, "_update_policy": { "total": 509.91431005400955, "count": 447, "self": 302.8242494070273, "children": { "TorchPPOOptimizer.update": { "total": 207.09006064698224, "count": 22893, "self": 207.09006064698224 } } } } } } }, "trainer_threads": { "total": 1.2289992810110562e-06, "count": 1, "self": 1.2289992810110562e-06 }, "TrainerController._save_models": { "total": 0.1282948429998214, "count": 1, "self": 0.002003808999688772, "children": { "RLTrainer._checkpoint": { "total": 0.12629103400013264, "count": 1, "self": 0.12629103400013264 } } } } } } }