{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.42745521664619446, "min": 0.42720916867256165, "max": 1.4355342388153076, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12734.74609375, "min": 12734.74609375, "max": 43548.3671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989996.0, "min": 29963.0, "max": 989996.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989996.0, "min": 29963.0, "max": 989996.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.49868324398994446, "min": -0.10083520412445068, "max": 0.4993745684623718, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 135.14315795898438, "min": -24.301284790039062, "max": 135.8298797607422, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.16643992066383362, "min": -0.16643992066383362, "max": 0.3781134784221649, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -45.10521697998047, "min": -45.10521697998047, "max": 90.74723815917969, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0672510928551977, "min": 0.06441611856227372, "max": 0.07397898587135107, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0087663928279655, "min": 0.5780115663366501, "max": 1.0549503255363863, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014534920859862016, "min": 0.000831639535990637, "max": 0.01668207340064088, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21802381289793024, "min": 0.011642953503868918, "max": 0.23354902760897234, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.469797510099998e-06, "min": 7.469797510099998e-06, "max": 0.0002948531642156125, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011204696265149997, "min": 0.00011204696265149997, "max": 0.003633345188884999, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024899, "min": 0.1024899, "max": 0.1982843875, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373485, "min": 1.4774446000000003, "max": 2.611115, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002587410099999999, "min": 0.0002587410099999999, "max": 0.00982861031125, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038811151499999986, "min": 0.0038811151499999986, "max": 0.12113038849999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01016462966799736, "min": 0.01016462966799736, "max": 0.5040149688720703, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1524694412946701, "min": 0.14933843910694122, "max": 4.0321197509765625, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 371.7564102564103, "min": 344.89156626506025, "max": 998.1875, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28997.0, "min": 16378.0, "max": 32971.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5491316163841682, "min": -0.9366438027936965, "max": 1.582799975681736, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 122.38139769434929, "min": -29.97260168939829, "max": 131.37239798158407, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5491316163841682, "min": -0.9366438027936965, "max": 1.582799975681736, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 122.38139769434929, "min": -29.97260168939829, "max": 131.37239798158407, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03969827307225352, "min": 0.03969827307225352, "max": 9.790487950996441, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1361635727080284, "min": 3.1361635727080284, "max": 166.4382951669395, "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": "1676138771", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1676140898" }, "total": 2127.2470620329996, "count": 1, "self": 0.4761281819996839, "children": { "run_training.setup": { "total": 0.11258154500001183, "count": 1, "self": 0.11258154500001183 }, "TrainerController.start_learning": { "total": 2126.658352306, "count": 1, "self": 1.2355610520285154, "children": { "TrainerController._reset_env": { "total": 7.393382454999937, "count": 1, "self": 7.393382454999937 }, "TrainerController.advance": { "total": 2117.938186805972, "count": 63702, "self": 1.3002901059498981, "children": { "env_step": { "total": 1389.1521536149585, "count": 63702, "self": 1279.7296319119591, "children": { "SubprocessEnvManager._take_step": { "total": 108.65265323303868, "count": 63702, "self": 4.437966436030706, "children": { "TorchPolicy.evaluate": { "total": 104.21468679700797, "count": 62563, "self": 35.21849018401247, "children": { "TorchPolicy.sample_actions": { "total": 68.9961966129955, "count": 62563, "self": 68.9961966129955 } } } } }, "workers": { "total": 0.7698684699605565, "count": 63702, "self": 0.0, "children": { "worker_root": { "total": 2122.246226348013, "count": 63702, "is_parallel": true, "self": 952.3636917520178, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024279140000089683, "count": 1, "is_parallel": true, "self": 0.000804686000037691, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016232279999712773, "count": 8, "is_parallel": true, "self": 0.0016232279999712773 } } }, "UnityEnvironment.step": { "total": 0.045676430999947115, "count": 1, "is_parallel": true, "self": 0.0005046929999252825, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004684689999976399, "count": 1, "is_parallel": true, "self": 0.0004684689999976399 }, "communicator.exchange": { "total": 0.04314309400001548, "count": 1, "is_parallel": true, "self": 0.04314309400001548 }, "steps_from_proto": { "total": 0.0015601750000087122, "count": 1, "is_parallel": true, "self": 0.0003747430000657914, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011854319999429208, "count": 8, "is_parallel": true, "self": 0.0011854319999429208 } } } } } } }, "UnityEnvironment.step": { "total": 1169.8825345959951, "count": 63701, "is_parallel": true, "self": 30.498246739882234, "children": { "UnityEnvironment._generate_step_input": { "total": 22.151474821022703, "count": 63701, "is_parallel": true, "self": 22.151474821022703 }, "communicator.exchange": { "total": 1017.6498551450472, "count": 63701, "is_parallel": true, "self": 1017.6498551450472 }, "steps_from_proto": { "total": 99.58295789004296, "count": 63701, "is_parallel": true, "self": 21.28035009095072, "children": { "_process_rank_one_or_two_observation": { "total": 78.30260779909224, "count": 509608, "is_parallel": true, "self": 78.30260779909224 } } } } } } } } } } }, "trainer_advance": { "total": 727.4857430850635, "count": 63702, "self": 2.3421099640694365, "children": { "process_trajectory": { "total": 157.21797140599574, "count": 63702, "self": 157.03181868299544, "children": { "RLTrainer._checkpoint": { "total": 0.18615272300030483, "count": 2, "self": 0.18615272300030483 } } }, "_update_policy": { "total": 567.9256617149983, "count": 455, "self": 218.9818677790322, "children": { "TorchPPOOptimizer.update": { "total": 348.94379393596614, "count": 22761, "self": 348.94379393596614 } } } } } } }, "trainer_threads": { "total": 1.1069996617152356e-06, "count": 1, "self": 1.1069996617152356e-06 }, "TrainerController._save_models": { "total": 0.09122088599997369, "count": 1, "self": 0.0015081299998200848, "children": { "RLTrainer._checkpoint": { "total": 0.0897127560001536, "count": 1, "self": 0.0897127560001536 } } } } } } }