{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1681683510541916, "min": 0.15530282258987427, "max": 1.4578778743743896, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5047.7412109375, "min": 4639.2060546875, "max": 44226.18359375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999896.0, "min": 29952.0, "max": 2999896.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999896.0, "min": 29952.0, "max": 2999896.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7509257793426514, "min": -0.11829188466072083, "max": 0.8692546486854553, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 225.27774047851562, "min": -28.508344650268555, "max": 267.7304382324219, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01579970121383667, "min": -0.02879728004336357, "max": 0.41903287172317505, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.73991060256958, "min": -7.141725540161133, "max": 99.310791015625, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06770078153515767, "min": 0.0632757695913279, "max": 0.07520686918098403, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9478109414922075, "min": 0.48656845042895497, "max": 1.0690805956968974, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015603785037889058, "min": 0.00034385671994276336, "max": 0.018794881926152623, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2184529905304468, "min": 0.003483868196546286, "max": 0.26759834508993663, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5894494702166694e-06, "min": 1.5894494702166694e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2252292583033373e-05, "min": 2.2252292583033373e-05, "max": 0.0038473116175628663, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10052978333333333, "min": 0.10052978333333333, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4074169666666667, "min": 1.3897045333333333, "max": 2.7824371333333335, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.292535500000011e-05, "min": 6.292535500000011e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008809549700000015, "min": 0.0008809549700000015, "max": 0.12826546962, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006413917988538742, "min": 0.006246405653655529, "max": 0.44566279649734497, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08979485183954239, "min": 0.08744967728853226, "max": 3.1196396350860596, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 233.1015625, "min": 201.45833333333334, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29837.0, "min": 15984.0, "max": 32981.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7668984201736748, "min": -1.0000000521540642, "max": 1.7846513756861289, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 226.16299778223038, "min": -32.000001668930054, "max": 267.5165982544422, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7668984201736748, "min": -1.0000000521540642, "max": 1.7846513756861289, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 226.16299778223038, "min": -32.000001668930054, "max": 267.5165982544422, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01560555958178611, "min": 0.014394460874730916, "max": 8.577814912423491, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.9975116264686221, "min": 1.959993901909911, "max": 137.24503859877586, "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": "1742867397", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742874801" }, "total": 7403.38290108, "count": 1, "self": 0.4968917079995663, "children": { "run_training.setup": { "total": 0.02303691500003424, "count": 1, "self": 0.02303691500003424 }, "TrainerController.start_learning": { "total": 7402.862972457, "count": 1, "self": 3.9640561028809316, "children": { "TrainerController._reset_env": { "total": 3.2292397979999805, "count": 1, "self": 3.2292397979999805 }, "TrainerController.advance": { "total": 7395.57944726512, "count": 194815, "self": 4.037500438104871, "children": { "env_step": { "total": 5283.6028627100895, "count": 194815, "self": 4831.9600436610335, "children": { "SubprocessEnvManager._take_step": { "total": 449.2831331748404, "count": 194815, "self": 13.563055269694019, "children": { "TorchPolicy.evaluate": { "total": 435.72007790514635, "count": 187567, "self": 435.72007790514635 } } }, "workers": { "total": 2.359685874215984, "count": 194815, "self": 0.0, "children": { "worker_root": { "total": 7388.279036670039, "count": 194815, "is_parallel": true, "self": 2893.2359805259675, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005363669999951526, "count": 1, "is_parallel": true, "self": 0.0038656609998497515, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014980090001017743, "count": 8, "is_parallel": true, "self": 0.0014980090001017743 } } }, "UnityEnvironment.step": { "total": 0.05141840700002831, "count": 1, "is_parallel": true, "self": 0.0005286750000550455, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004358649999858244, "count": 1, "is_parallel": true, "self": 0.0004358649999858244 }, "communicator.exchange": { "total": 0.048733513999991374, "count": 1, "is_parallel": true, "self": 0.048733513999991374 }, "steps_from_proto": { "total": 0.0017203529999960665, "count": 1, "is_parallel": true, "self": 0.00048701399998662964, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012333390000094369, "count": 8, "is_parallel": true, "self": 0.0012333390000094369 } } } } } } }, "UnityEnvironment.step": { "total": 4495.043056144072, "count": 194814, "is_parallel": true, "self": 97.46818754395008, "children": { "UnityEnvironment._generate_step_input": { "total": 69.36047836981254, "count": 194814, "is_parallel": true, "self": 69.36047836981254 }, "communicator.exchange": { "total": 4042.316074984931, "count": 194814, "is_parallel": true, "self": 4042.316074984931 }, "steps_from_proto": { "total": 285.89831524537715, "count": 194814, "is_parallel": true, "self": 56.56566193686194, "children": { "_process_rank_one_or_two_observation": { "total": 229.3326533085152, "count": 1558512, "is_parallel": true, "self": 229.3326533085152 } } } } } } } } } } }, "trainer_advance": { "total": 2107.939084116925, "count": 194815, "self": 8.324814065802002, "children": { "process_trajectory": { "total": 397.89394187311257, "count": 194815, "self": 397.26552603811126, "children": { "RLTrainer._checkpoint": { "total": 0.6284158350013058, "count": 6, "self": 0.6284158350013058 } } }, "_update_policy": { "total": 1701.7203281780107, "count": 1386, "self": 934.3657998479897, "children": { "TorchPPOOptimizer.update": { "total": 767.354528330021, "count": 68361, "self": 767.354528330021 } } } } } } }, "trainer_threads": { "total": 9.279992809752002e-07, "count": 1, "self": 9.279992809752002e-07 }, "TrainerController._save_models": { "total": 0.09022836300027848, "count": 1, "self": 0.0017416930004401365, "children": { "RLTrainer._checkpoint": { "total": 0.08848666999983834, "count": 1, "self": 0.08848666999983834 } } } } } } }