{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5111764669418335, "min": 0.5111764669418335, "max": 1.3763642311096191, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15302.578125, "min": 15302.578125, "max": 41753.38671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989909.0, "min": 29952.0, "max": 989909.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989909.0, "min": 29952.0, "max": 989909.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4948144853115082, "min": -0.09361627697944641, "max": 0.5173130035400391, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 133.59991455078125, "min": -22.655139923095703, "max": 140.1918182373047, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014236483722925186, "min": -0.07928085327148438, "max": 0.49544256925582886, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.843850612640381, "min": -21.485111236572266, "max": 117.41989135742188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06646509808100139, "min": 0.06598758987439353, "max": 0.07447238116167552, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9305113731340194, "min": 0.5023804677649664, "max": 1.0787041993559492, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014028587367474322, "min": 0.0008511170174885417, "max": 0.014028587367474322, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1964002231446405, "min": 0.011915638244839584, "max": 0.1964002231446405, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.682540296328575e-06, "min": 7.682540296328575e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010755556414860006, "min": 0.00010755556414860006, "max": 0.0036335107888298, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025608142857143, "min": 0.1025608142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358514000000002, "min": 1.3886848, "max": 2.611170200000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026582534714285734, "min": 0.00026582534714285734, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003721554860000003, "min": 0.003721554860000003, "max": 0.12113590298000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008870408870279789, "min": 0.008870408870279789, "max": 0.4211749732494354, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1241857260465622, "min": 0.1241857260465622, "max": 2.9482247829437256, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 366.9746835443038, "min": 366.9746835443038, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28991.0, "min": 15984.0, "max": 33686.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5570531441252442, "min": -1.0000000521540642, "max": 1.5907721280863014, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 123.0071983858943, "min": -29.83800170570612, "max": 125.6709981188178, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5570531441252442, "min": -1.0000000521540642, "max": 1.5907721280863014, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 123.0071983858943, "min": -29.83800170570612, "max": 125.6709981188178, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03341580830712263, "min": 0.03341580830712263, "max": 7.4758562706410885, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.639848856262688, "min": 2.639848856262688, "max": 119.61370033025742, "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": "1679669163", "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", "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": "1679671293" }, "total": 2129.684761696, "count": 1, "self": 0.48157280399982483, "children": { "run_training.setup": { "total": 0.17355113100006747, "count": 1, "self": 0.17355113100006747 }, "TrainerController.start_learning": { "total": 2129.0296377610002, "count": 1, "self": 1.539033614994878, "children": { "TrainerController._reset_env": { "total": 7.300176039999997, "count": 1, "self": 7.300176039999997 }, "TrainerController.advance": { "total": 2120.0984501800053, "count": 63660, "self": 1.5850444859966046, "children": { "env_step": { "total": 1494.924199659031, "count": 63660, "self": 1380.9081529441573, "children": { "SubprocessEnvManager._take_step": { "total": 113.10353976295096, "count": 63660, "self": 4.7840848619835015, "children": { "TorchPolicy.evaluate": { "total": 108.31945490096746, "count": 62555, "self": 108.31945490096746 } } }, "workers": { "total": 0.9125069519227509, "count": 63660, "self": 0.0, "children": { "worker_root": { "total": 2124.1015011089235, "count": 63660, "is_parallel": true, "self": 863.9014780878895, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023266220000550675, "count": 1, "is_parallel": true, "self": 0.0006462729995746486, "children": { "_process_rank_one_or_two_observation": { "total": 0.001680349000480419, "count": 8, "is_parallel": true, "self": 0.001680349000480419 } } }, "UnityEnvironment.step": { "total": 0.045389075000002777, "count": 1, "is_parallel": true, "self": 0.0005103779997170932, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005086470000605914, "count": 1, "is_parallel": true, "self": 0.0005086470000605914 }, "communicator.exchange": { "total": 0.04280294300019705, "count": 1, "is_parallel": true, "self": 0.04280294300019705 }, "steps_from_proto": { "total": 0.0015671070000280451, "count": 1, "is_parallel": true, "self": 0.000337766999791711, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012293400002363342, "count": 8, "is_parallel": true, "self": 0.0012293400002363342 } } } } } } }, "UnityEnvironment.step": { "total": 1260.200023021034, "count": 63659, "is_parallel": true, "self": 31.420505986036915, "children": { "UnityEnvironment._generate_step_input": { "total": 22.781952241014096, "count": 63659, "is_parallel": true, "self": 22.781952241014096 }, "communicator.exchange": { "total": 1113.7038721479755, "count": 63659, "is_parallel": true, "self": 1113.7038721479755 }, "steps_from_proto": { "total": 92.29369264600746, "count": 63659, "is_parallel": true, "self": 20.097022200014862, "children": { "_process_rank_one_or_two_observation": { "total": 72.1966704459926, "count": 509272, "is_parallel": true, "self": 72.1966704459926 } } } } } } } } } } }, "trainer_advance": { "total": 623.5892060349777, "count": 63660, "self": 2.872228233972237, "children": { "process_trajectory": { "total": 119.39238245900333, "count": 63660, "self": 119.19196807200296, "children": { "RLTrainer._checkpoint": { "total": 0.2004143870003645, "count": 2, "self": 0.2004143870003645 } } }, "_update_policy": { "total": 501.3245953420021, "count": 452, "self": 319.95333977299856, "children": { "TorchPPOOptimizer.update": { "total": 181.37125556900355, "count": 22758, "self": 181.37125556900355 } } } } } } }, "trainer_threads": { "total": 8.870001693139784e-07, "count": 1, "self": 8.870001693139784e-07 }, "TrainerController._save_models": { "total": 0.09197703900008491, "count": 1, "self": 0.0013599760004581185, "children": { "RLTrainer._checkpoint": { "total": 0.0906170629996268, "count": 1, "self": 0.0906170629996268 } } } } } } }