{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.29890257120132446, "min": 0.2798689603805542, "max": 0.690678060054779, "count": 34 }, "Pyramids.Policy.Entropy.sum": { "value": 8947.947265625, "min": 6837.51416015625, "max": 20687.189453125, "count": 34 }, "Pyramids.Step.mean": { "value": 1499928.0, "min": 509984.0, "max": 1499928.0, "count": 34 }, "Pyramids.Step.sum": { "value": 1499928.0, "min": 509984.0, "max": 1499928.0, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6424160599708557, "min": -0.07951540499925613, "max": 0.7126874327659607, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 183.0885772705078, "min": -19.163211822509766, "max": 209.5301055908203, "count": 34 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.006785540841519833, "min": -0.012906786054372787, "max": 0.03882264718413353, "count": 34 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.9338791370391846, "min": -3.639713764190674, "max": 10.443291664123535, "count": 34 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 300.40776699029124, "min": 158.0, "max": 972.09375, "count": 34 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30942.0, "min": 474.0, "max": 33200.0, "count": 34 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.680166977267821, "min": -0.7852750485762954, "max": 1.8419999827941258, "count": 34 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 173.05719865858555, "min": -25.128801554441452, "max": 195.44419772922993, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.680166977267821, "min": -0.7852750485762954, "max": 1.8419999827941258, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 173.05719865858555, "min": -25.128801554441452, "max": 195.44419772922993, "count": 34 }, "Pyramids.Policy.RndReward.mean": { "value": 0.031643046891880196, "min": 0.029883607279324473, "max": 0.17481861807382068, "count": 34 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2592338298636605, "min": 0.14030545111745596, "max": 6.817926104879007, "count": 34 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06658352132720667, "min": 0.06625723796691198, "max": 0.07332178857824248, "count": 34 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9321692985808934, "min": 0.21996536573472744, "max": 1.0763413148992649, "count": 34 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01617559841306553, "min": 0.0017751062543497832, "max": 0.01617559841306553, "count": 34 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2264583777829174, "min": 0.0211898731298182, "max": 0.23511970965288737, "count": 34 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.1718132284761884e-06, "min": 3.1718132284761884e-06, "max": 0.0001991639002787111, "count": 34 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.440538519866664e-05, "min": 4.440538519866664e-05, "max": 0.0027301714899430002, "count": 34 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10105723809523813, "min": 0.10105723809523813, "max": 0.16638795555555558, "count": 34 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4148013333333338, "min": 0.49916386666666673, "max": 2.3100570000000005, "count": 34 }, "Pyramids.Policy.Beta.mean": { "value": 0.00011561808571428563, "min": 0.00011561808571428563, "max": 0.00664215676, "count": 34 }, "Pyramids.Policy.Beta.sum": { "value": 0.0016186531999999988, "min": 0.0016186531999999988, "max": 0.0910546943, "count": 34 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010202839970588684, "min": 0.010060305707156658, "max": 0.020084787160158157, "count": 34 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14283975958824158, "min": 0.05922834575176239, "max": 0.2811870276927948, "count": 34 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679882068", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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 --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1679885401" }, "total": 3332.302809297, "count": 1, "self": 0.5953055580002911, "children": { "run_training.setup": { "total": 0.13212189299974852, "count": 1, "self": 0.13212189299974852 }, "TrainerController.start_learning": { "total": 3331.575381846, "count": 1, "self": 2.333438276002198, "children": { "TrainerController._reset_env": { "total": 5.435023740999895, "count": 1, "self": 5.435023740999895 }, "TrainerController.advance": { "total": 3323.6996491129976, "count": 64337, "self": 2.5265376661873233, "children": { "env_step": { "total": 2247.403280915897, "count": 64337, "self": 2114.6026447800486, "children": { "SubprocessEnvManager._take_step": { "total": 131.37163090778722, "count": 64337, "self": 6.562056770887466, "children": { "TorchPolicy.evaluate": { "total": 124.80957413689976, "count": 62549, "self": 124.80957413689976 } } }, "workers": { "total": 1.4290052280612144, "count": 64337, "self": 0.0, "children": { "worker_root": { "total": 3324.3106096400124, "count": 64337, "is_parallel": true, "self": 1379.4548536519178, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003024829999958456, "count": 1, "is_parallel": true, "self": 0.0008231780002461164, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022016519997123396, "count": 8, "is_parallel": true, "self": 0.0022016519997123396 } } }, "UnityEnvironment.step": { "total": 0.09306360099981248, "count": 1, "is_parallel": true, "self": 0.0006208509994394262, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005132300002514967, "count": 1, "is_parallel": true, "self": 0.0005132300002514967 }, "communicator.exchange": { "total": 0.08995682099975966, "count": 1, "is_parallel": true, "self": 0.08995682099975966 }, "steps_from_proto": { "total": 0.0019726990003618994, "count": 1, "is_parallel": true, "self": 0.00044938199971511494, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015233170006467844, "count": 8, "is_parallel": true, "self": 0.0015233170006467844 } } } } } } }, "UnityEnvironment.step": { "total": 1944.8557559880946, "count": 64336, "is_parallel": true, "self": 42.58033807901211, "children": { "UnityEnvironment._generate_step_input": { "total": 26.081649256087076, "count": 64336, "is_parallel": true, "self": 26.081649256087076 }, "communicator.exchange": { "total": 1750.0566777308204, "count": 64336, "is_parallel": true, "self": 1750.0566777308204 }, "steps_from_proto": { "total": 126.13709092217505, "count": 64336, "is_parallel": true, "self": 28.810998218191344, "children": { "_process_rank_one_or_two_observation": { "total": 97.3260927039837, "count": 514688, "is_parallel": true, "self": 97.3260927039837 } } } } } } } } } } }, "trainer_advance": { "total": 1073.7698305309132, "count": 64337, "self": 4.693636518783933, "children": { "process_trajectory": { "total": 151.88804837512998, "count": 64337, "self": 151.66285565312955, "children": { "RLTrainer._checkpoint": { "total": 0.22519272200042906, "count": 2, "self": 0.22519272200042906 } } }, "_update_policy": { "total": 917.1881456369993, "count": 470, "self": 393.269350020998, "children": { "TorchPPOOptimizer.update": { "total": 523.9187956160013, "count": 22740, "self": 523.9187956160013 } } } } } } }, "trainer_threads": { "total": 1.1020001693395898e-06, "count": 1, "self": 1.1020001693395898e-06 }, "TrainerController._save_models": { "total": 0.10726961399996071, "count": 1, "self": 0.0024033519985096063, "children": { "RLTrainer._checkpoint": { "total": 0.1048662620014511, "count": 1, "self": 0.1048662620014511 } } } } } } }